PhD in Computer Science
Stanford University, 1999
Black-Box Prompt Learning for Pre-trained Language Models
Article
Article
Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity
Conference paper
Hashtag-Guided Low-Resource Tweet Classification
Conference paper
Conference paper
Particle-based Variational Inference with Preconditioned Functional Gradient Flow
Conference paper
A stochastic extra-step quasi-Newton method for nonsmooth nonconvex optimization
Article
Convex Formulation of Overparameterized Deep Neural Networks
Article
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning
Article
Weakly Supervised Disentangled Generative Causal Representation Learning
Article
Article
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
Conference paper
Conference paper
Achieving Minimax Rates in Pool-Based Batch Active Learning
Conference paper
Bayesian Invariant Risk Minimization
Conference paper
Conference paper
Conference paper
Exploring Geometric Consistency for Monocular 3D Object Detection
Conference paper
HYPERDQN: A Randomized Exploration Method for Deep Reinforcement Learning
Conference paper
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Conference paper
Minimax Regret Optimization for Robust Machine Learning under Distribution Shift
Conference paper
Model Agnostic Sample Reweighting for Out-of-Distribution Learning
Conference paper
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity
Conference paper
Multilingual Word Sense Disambiguation with Unified Sense Representation
Conference paper
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
Conference paper
Conference paper
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
Conference paper
Probabilistic Bilevel Coreset Selection
Conference paper
Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting
Conference paper
Semi-supervised Monocular 3D Object Detection by Multi-view Consistency
Conference paper
Sparse Invariant Risk Minimization
Conference paper
A Framework of Composite Functional Gradient Methods for Generative Adversarial Models
Article
DeEPCA: Decentralized Exact PCA with Linear Convergence Rate
Article
Article
Local-global memory neural network for medication prediction
Article
Mathematical Models of Overparameterized Neural Networks
Article
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning
Conference paper
DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
Conference paper
Effective Sparsification of Neural Networks with Global Sparsity Constraint
Conference paper
Efficient Neural Network Training via Forward and Backward Propagation Sparsification
Conference paper
Error Compensated Distributed SGD can be Accelerated
Conference paper
Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling
Conference paper
Conference paper
Involution: Inverting the inherence of convolution for visual recognition
Conference paper
Involution: Inverting the Inherence of Convolution for Visual Recognition
Conference paper
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Conference paper
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
Conference paper
Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation
Conference paper
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation
Conference paper
Conference paper
Accelerated dual-averaging primal–dual method for composite convex minimization
Article
Article
Local Uncertainty Sampling for Large-Scale Multiclass Logistic Regression
Article
MAP Inference Via ℓ_{2} -Sphere Linear Program Reformulation
Article
Proximal Gradient Method for Nonsmooth Optimization Over the Stiefel Manifold
Article
A generalized neural tangent kernel analysis for two-layer neural networks
Conference paper
Black-Box Adversarial Attack with Transferable Model-based Embedding
Conference paper
Bridging the gap between sample-based and one-shot neural architecture search with BONAS
Conference paper
CATCH: Context-Based Meta Reinforcement Learning for Transferrable Architecture Search
Conference paper
Decentralized accelerated proximal gradient descent
Conference paper
Conference paper
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
Conference paper
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
Conference paper
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks
Conference paper
Improving Chinese word segmentation with wordhood memory networks
Conference paper
Conference paper
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
Conference paper
Model Rubik’s cube: Twisting Resolution, Depth and Width for TinyNets
Conference paper
Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts
Conference paper
Stable Learning via Differentiated Variable Decorrelation
Conference paper
Stable Learning via Sample Reweighting
Conference paper
Conference paper
Conference paper
ZEN: Pre-Training Chinese Text Encoder Enhanced by N-gram Representations
Conference paper
Article
Article
Robust Frequent Directions with Application in Online Learning
Article
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
Article
Utilizing Second Order Information in Minibatch Stochastic Variance Reduced Proximal Iterations
Article
DHER: Hindsight experience replay for dynamic goals
Conference paper
Divergence-augmented policy optimization
Conference paper
Doublesqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Conference paper
Doublesqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Conference paper
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
Conference paper
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI
Conference paper
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI
Conference paper
Conference paper
Conference paper
Reinforced Training Data Selection for Domain Adaptation
Conference paper
A convex formulation for high-dimensional sparse sliced inverse regression
Article
Bayesian Model Averaging with Exponentiated Least Squares Loss
Article
Gradient hard thresholding pursuit
Article
I-LAMM for sparse learning: Simultaneous control of algorithmic complexity and statistical error
Article
Learning to remember translation history with a continuous cache
Article
Near-optimal stochastic approximation for online principal component estimation
Article
Pathwise coordinate optimization for sparse learning: Algorithm and theory
Article
Sparse generalized eigenvalue problem: optimal statistical rates via truncated Rayleigh flow
Article
An algorithmic framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-gradient method
Conference paper
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
Conference paper
Candidates vs. noises estimation for large multi-class classification problem
Conference paper
Candidates vs. noises estimation for large multi-class classification problem
Conference paper
Communication compression for decentralized training
Conference paper
Composite functional gradient learning of generative adversarial models
Conference paper
Composite Functional Gradient Learning of Generative Adversarial Models
Conference paper
End-to-end active object tracking via reinforcement learning
Conference paper
End-to-end active object tracking via reinforcement learning
Conference paper
Error compensated quantized sgd and its applications to large-scale distributed optimization
Conference paper
Error compensated quantized SGD and its applications to large-scale distributed optimization
Conference paper
Exponentially weighted imitation learning for batched historical data
Conference paper
Fully decentralized multi-agent reinforcement learning with networked agents
Conference paper
Fully decentralized multi-agent reinforcement learning with networked agents
Conference paper
Gradient sparsification for communication-efficient distributed optimization
Conference paper
Graphical nonconvex optimization via an adaptive convex relaxation
Conference paper
Graphical nonconvex optimization via an adaptive convex relaxation
Conference paper
Near-optimal non-convex optimization via stochastic path integrated differential estimator
Conference paper
Safe element screening for submodular function minimization
Conference paper
Safe Element Screening for Submodular Function Minimization
Conference paper
Stochastic expectation maximization with variance reduction
Conference paper
Stochastic primal-dual method for empirical risk minimization with O(1) per-iteration complexity
Conference paper
A general distributed dual coordinate optimization framework for regularized loss minimization
Article
Hierarchical Contextual Attention Recurrent Neural Network for Map Query Suggestion
Article
Deep pyramid convolutional neural networks for text categorization
Conference paper
Diffusion approximations for online principal component estimation and global convergence
Conference paper
Efficient distributed learning with sparsity
Conference paper
Efficient distributed learning with sparsity
Conference paper
On quadratic convergence of DC proximal Newton algorithm in nonconvex sparse learning
Conference paper
Projection-free distributed online learning in networks
Conference paper
Projection-free distributed online learning in networks
Conference paper
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Article
Towards more efficient SPSD matrix approximation and CUR matrix decomposition
Article
Exact recovery of hard thresholding pursuit
Conference paper
Fast Component Pursuit for Large-scale Inverse Covariance Estimation
Conference paper
Conference paper
Learning Additive Exponential Family Graphical Models via ℓ_{2,1}-norm Regularized M-Estimation
Conference paper
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity
Conference paper
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity
Conference paper
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization
Conference paper
Supervised and semi-supervised text categorization using LSTM for region embeddings
Conference paper
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
Conference paper
Learning sparse low-threshold linear classifiers
Article
Adaptive stochastic alternating direction method of multipliers
Conference paper
Adaptive stochastic alternating direction method of multipliers
Conference paper
Crowd fraud detection in internet advertising
Conference paper
Effective use of word order for text categorization with convolutional neural networks
Conference paper
Local smoothness in variance reduced optimization
Conference paper
Quartz: Randomized dual coordinate ascent with arbitrary sampling
Conference paper
Semi-supervised convolutional neural networks for text categorization via region embedding
Conference paper
Stochastic optimization with importance sampling for regularized loss minimization
Conference paper
A proximal stochastic gradient method with progressive variance reduction
Article
Learning nonlinear functions using regularized greedy forest
Article
Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
Article
Partial Gaussian graphical model estimation
Article
Random Design Analysis of Ridge Regression
Article
A convergence rate analysis for LogitBoost, MART and their variant
Conference paper
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Conference paper
Communication-efficient distributed optimization using an approximate Newton-type method
Conference paper
Compressed counting meets compressed sensing
Conference paper
Efficient mini-batch training for stochastic optimization
Conference paper
Gradient hard thresholding pursuit for sparsity-constrained optimization
Conference paper
A Joint Matrix Completion and Filtering Model for Influenza Serological Data Integration
Article
A proximal-gradient homotopy method for the sparse least-squares problem
Article
Multi-stage convex relaxation for feature selection
Article
Stochastic Dual Coordinate Ascent methods for regularized loss minimization
Article
Truncated power method for sparse eigenvalue problems
Article
Accelerated mini-batch stochastic dual coordinate ascent
Conference paper
Accelerating stochastic gradient descent using predictive variance reduction
Conference paper
High-dimensional joint sparsity random effects model for multi-task learning
Conference paper
Conference paper
A General theory of concave regularization for high-dimensional sparse estimation problems
Article
A spectral algorithm for learning Hidden Markov Models
Article
A tail inequality for quadratic forms of subgaussian random vectors
Article
Deviation optimal learning using greedy q-aggregation
Article
Article
Tail inequalities for sums of random matrices that depend on the intrinsic dimension
Article
A proximal-gradient homotopy method for the ℓ 1-regularized least-squares problem
Conference paper
Random design analysis of ridge regression
Conference paper
Selective labeling via error bound minimization
Conference paper
Adaptive forward-backward greedy algorithm for learning sparse representations
Article
Concepts and applications for influenza antigenic cartography
Article
Integrative analysis of many weighted Co-Expression networks using tensor computation
Article
Learning with structured sparsity
Article
Robust matrix decomposition with sparse corruptions
Article
Sparse recovery with orthogonal matching pursuit under RIP
Article
Efficient optimal learning for contextual bandits
Conference paper
Conference paper
Learning to search efficiently in high dimensions
Conference paper
Spectral methods for learning multivariate latent tree structure
Conference paper
A computational framework for influenza antigenic cartography
Article
Analysis of multi-stage convex relaxation for sparse regularization
Article
Article
Trading accuracy for sparsity in optimization problems with sparsity constraints
Article
Fundamental statistical techniques
Book chapter
Agnostic active learning without constraints
Conference paper
Conference paper
Image classification using supervector coding of local image descriptors
Conference paper
Improved local coordinate coding using local tangents
Conference paper
Classifying search quries using the web as a source of knowledge.
Article
On the consistency of feature selection using greedy least squares regression
Article
Some sharp performance bounds for least squares regression with L_{1} regularization
Article
Sparse Online Learning via Truncated Gradient
Article
A spectral algorithm for learning hidden Markov models
Conference paper
Learning nonlinear dynamic models
Conference paper
Learning with structured sparsity
Conference paper
Multi-label prediction via compressed sensing
Conference paper
Nonlinear learning using local coordinate coding
Conference paper
An online relevant set algorithm for statistical machine translation
Article
Graph-based semi-supervised learning and spectral kernel design
Article
Statistical analysis of Bayes optimal subset ranking
Article
Adaptive forward-backward greedy algorithm for sparse learning with linear models
Conference paper
Multi-stage convex relaxation for learning with sparse regularization
Conference paper
Sparse online learning via truncated gradient
Conference paper
A block bigram prediction model for statistical machine translation
Article
On the effectiveness of Laplacian normalization for graph semi-supervised learning
Article
A general boosting method and its application to learning ranking functions for Web search
Conference paper
Epoch-Greedy algorithm for multi-armed bandits with side information
Conference paper
Conference paper
Robust classification of rare queries using web knowledge
Conference paper
Two-view feature generation model for semi-supervised learning
Conference paper
From ε-entropy to KL-entropy: Analysis of minimum information complexity density estimation
Article
Information theoretical upper and lower bounds for statistical estimation
Article
A discriminative global training algorithm for statistical MT
Conference paper
Learning on graph with Laplacian regularization
Conference paper
Linear prediction models with graph regularization for Web-page categorization
Conference paper
Subset ranking using regression
Conference paper
A framework for learning predictive structures from multiple tasks and unlabeled data
Article
Boosting with early stopping: Convergence and consistency
Article
Learning bounds for kernel regression using effective data dimensionality
Article
Text mining: Predictive methods for analyzing unstructured information
Book
A high-performance semi-supervised learning method for text chunking
Conference paper
A localized prediction model for statistical machine translation
Conference paper
Analysis of spectral kernel design based semi-supervised learning
Conference paper
Data dependent concentration bounds for sequential prediction algorithms
Conference paper
Localized upper and lower bounds for some estimation problems
Conference paper
TREC 2005 genomics track experiments at IBM watson
Conference paper
Greedy algorithms for classification - Consistency, convergence rates, and adaptivity
Article
Statistical analysis of some multi-category large margin classification methods
Article
Statistical behavior and consistency of classification methods based on convex risk minimization
Article
Text categorization for a comprehensive time-dependent benchmark
Article
An evaluation of over-the-counter medication sales for syndromic surveillance
Conference paper
An infinity-sample theory for multi-category large margin classification
Conference paper
Conference paper
Column-generation boosting methods for mixture of kernels
Conference paper
Focused named entity recognition using machine learning
Conference paper
Generalization error bounds for Bayesian mixture algorithms
Conference paper
Learning bounds for a generalized family of Bayesian posterior distributions
Conference paper
On the convergence of MDL density estimation
Conference paper
Solving large scale linear prediction problems using stochastic gradient descent algorithms
Conference paper
Support vector classification with input data uncertainty
Conference paper
Leave-one-out bounds for kernel methods
Article
Sequential greedy approximation for certain convex optimization problems
Article
Performance analysis and evaluation
Book chapter
A robust risk minimization based named entity recognition system
Conference paper
Data-dependent bounds for Bayesian mixture methods
Conference paper
Howtogetachinesename (entity): Segmentation and combination issues.
Conference paper
Named entity recogintion through classifier combination
Conference paper
On the Convergence of Boosting Procedures
Conference paper
Updating an nlp system to fit new domains: an empirical study on the sentence segmentation problem
Conference paper
A decision-tree-based symbolic rule induction system for text categorization
Article
Approximation bounds for some sparse kernel regression algorithms
Article
Covering Number Bounds of Certain Regularized Linear Function Classes
Article
On the consistency of instantaneous rigid motion estimation
Article
On the dual formulation of regularized linear systems
Article
Recommender Systems Using Linear Classifiers
Article
Text Chunking based on a Generalization of Winnow
Article
Two-Sided Arnoldi and Nonsymmetric Lanczos Algorithms
Article
Effective dimension and generalization of kernel learning
Conference paper
Generalization performance of some learning problems in hilbert functional spaces
Conference paper
Statistical behavior and consistency of support vector machines, boosting, and beyond
Conference paper
The consistency of greedy algorithms for classification
Conference paper
Rank-one approximation to high order tensors
Article
Text Categorization Based on Regularized Linear Classification Methods
Article
A general greedy approximation algorithm with applications
Conference paper
A leave-one-out cross validation bound for kernel methods with applications in learning
Conference paper
Conference paper
Convergence of large margin separable linear classification
Conference paper
Empirical study of recommender systems using linear classifiers
Conference paper
Conference paper
Some sparse approximation bounds for regression problems
Conference paper
Text chunking using regularized Winnow
Conference paper
Article
A probability analysis on the value of unlabeled data for classification problems
Conference paper
Active learning using adaptive resampling
Conference paper
Large margin Winnow methods for text categorization
Conference paper
Subspace iterative methods for eigenvalue problems
Article
Fast, robust, and consistent camera motion estimation
Conference paper
Some theoretical results concerning the convergence of composition of regularizated linear functions
Conference paper
Theoretical analysis of a class of randomized regularization methods
Conference paper
Eigenvalue perturbation and the generalized Krylov subspace method
Article
On the Homotopy Method for Perturbed Symmetric Generalized Eigenvalue Problems
Article
A linear algorithm for optimal context clustering with application to bi-level image coding
Conference paper
Compression by model combination
Conference paper
Model reduction for peec models including retardation
Conference paper
A progressive ziv-lempel algorithm for image compression
Conference paper
Progressive Ziv-Lempel Encoding of Synthetic Images
Conference paper
Optimal surface smoothing as filter design
Conference paper
Densities of self-similar measures on the line
Article
A stochastic extra-step quasi-Newton method for nonsmooth nonconvex optimization
Convex Formulation of Overparameterized Deep Neural Networks
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning
Weakly Supervised Disentangled Generative Causal Representation Learning
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games
Exploring Geometric Consistency for Monocular 3D Object Detection
HYPERDQN: A Randomized Exploration Method for Deep Reinforcement Learning
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
Minimax Regret Optimization for Robust Machine Learning under Distribution Shift
Model Agnostic Sample Reweighting for Out-of-Distribution Learning
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity
Multilingual Word Sense Disambiguation with Unified Sense Representation
Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting
Semi-supervised Monocular 3D Object Detection by Multi-view Consistency
A Framework of Composite Functional Gradient Methods for Generative Adversarial Models
DeEPCA: Decentralized Exact PCA with Linear Convergence Rate
Local-global memory neural network for medication prediction
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning
DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
Effective Sparsification of Neural Networks with Global Sparsity Constraint
Efficient Neural Network Training via Forward and Backward Propagation Sparsification
Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling
Involution: Inverting the inherence of convolution for visual recognition
Involution: Inverting the Inherence of Convolution for Visual Recognition
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation
Accelerated dual-averaging primal–dual method for composite convex minimization
Local Uncertainty Sampling for Large-Scale Multiclass Logistic Regression
MAP Inference Via ℓ_{2} -Sphere Linear Program Reformulation
Proximal Gradient Method for Nonsmooth Optimization Over the Stiefel Manifold
A generalized neural tangent kernel analysis for two-layer neural networks
Black-Box Adversarial Attack with Transferable Model-based Embedding
Bridging the gap between sample-based and one-shot neural architecture search with BONAS
CATCH: Context-Based Meta Reinforcement Learning for Transferrable Architecture Search
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks
Improving Chinese word segmentation with wordhood memory networks
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
Model Rubik’s cube: Twisting Resolution, Depth and Width for TinyNets
Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts
ZEN: Pre-Training Chinese Text Encoder Enhanced by N-gram Representations
Robust Frequent Directions with Application in Online Learning
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
Utilizing Second Order Information in Minibatch Stochastic Variance Reduced Proximal Iterations
Doublesqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Doublesqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI
Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI
A convex formulation for high-dimensional sparse sliced inverse regression
Bayesian Model Averaging with Exponentiated Least Squares Loss
I-LAMM for sparse learning: Simultaneous control of algorithmic complexity and statistical error
Learning to remember translation history with a continuous cache
Near-optimal stochastic approximation for online principal component estimation
Pathwise coordinate optimization for sparse learning: Algorithm and theory
Sparse generalized eigenvalue problem: optimal statistical rates via truncated Rayleigh flow
An algorithmic framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-gradient method
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
Candidates vs. noises estimation for large multi-class classification problem
Candidates vs. noises estimation for large multi-class classification problem
Composite functional gradient learning of generative adversarial models
Composite Functional Gradient Learning of Generative Adversarial Models
End-to-end active object tracking via reinforcement learning
End-to-end active object tracking via reinforcement learning
Error compensated quantized sgd and its applications to large-scale distributed optimization
Error compensated quantized SGD and its applications to large-scale distributed optimization
Exponentially weighted imitation learning for batched historical data
Fully decentralized multi-agent reinforcement learning with networked agents
Fully decentralized multi-agent reinforcement learning with networked agents
Gradient sparsification for communication-efficient distributed optimization
Graphical nonconvex optimization via an adaptive convex relaxation
Graphical nonconvex optimization via an adaptive convex relaxation
Near-optimal non-convex optimization via stochastic path integrated differential estimator
Stochastic primal-dual method for empirical risk minimization with O(1) per-iteration complexity
A general distributed dual coordinate optimization framework for regularized loss minimization
Hierarchical Contextual Attention Recurrent Neural Network for Map Query Suggestion
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Towards more efficient SPSD matrix approximation and CUR matrix decomposition
Fast Component Pursuit for Large-scale Inverse Covariance Estimation
Learning Additive Exponential Family Graphical Models via ℓ_{2,1}-norm Regularized M-Estimation
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization
Supervised and semi-supervised text categorization using LSTM for region embeddings
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
Adaptive stochastic alternating direction method of multipliers
Adaptive stochastic alternating direction method of multipliers
Effective use of word order for text categorization with convolutional neural networks
Quartz: Randomized dual coordinate ascent with arbitrary sampling
Semi-supervised convolutional neural networks for text categorization via region embedding
Stochastic optimization with importance sampling for regularized loss minimization
A proximal stochastic gradient method with progressive variance reduction
Learning nonlinear functions using regularized greedy forest
Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
A convergence rate analysis for LogitBoost, MART and their variant
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Communication-efficient distributed optimization using an approximate Newton-type method
Gradient hard thresholding pursuit for sparsity-constrained optimization
A Joint Matrix Completion and Filtering Model for Influenza Serological Data Integration
A proximal-gradient homotopy method for the sparse least-squares problem
Stochastic Dual Coordinate Ascent methods for regularized loss minimization
A computational framework for influenza antigenic cartography
Analysis of multi-stage convex relaxation for sparse regularization
Trading accuracy for sparsity in optimization problems with sparsity constraints
A block bigram prediction model for statistical machine translation
On the effectiveness of Laplacian normalization for graph semi-supervised learning
A framework for learning predictive structures from multiple tasks and unlabeled data
Learning bounds for kernel regression using effective data dimensionality
A high-performance semi-supervised learning method for text chunking
A localized prediction model for statistical machine translation
Analysis of spectral kernel design based semi-supervised learning
Data dependent concentration bounds for sequential prediction algorithms
Localized upper and lower bounds for some estimation problems
Greedy algorithms for classification - Consistency, convergence rates, and adaptivity
Statistical analysis of some multi-category large margin classification methods
Statistical behavior and consistency of classification methods based on convex risk minimization
Text categorization for a comprehensive time-dependent benchmark
An evaluation of over-the-counter medication sales for syndromic surveillance
An infinity-sample theory for multi-category large margin classification
Learning bounds for a generalized family of Bayesian posterior distributions
Solving large scale linear prediction problems using stochastic gradient descent algorithms
A decision-tree-based symbolic rule induction system for text categorization
Approximation bounds for some sparse kernel regression algorithms
Covering Number Bounds of Certain Regularized Linear Function Classes
A general distributed dual coordinate optimization framework for regularized loss minimization
Article
Hierarchical Contextual Attention Recurrent Neural Network for Map Query Suggestion
Article
Deep pyramid convolutional neural networks for text categorization
Conference paper
Diffusion approximations for online principal component estimation and global convergence
Conference paper
Efficient distributed learning with sparsity
Conference paper
Efficient distributed learning with sparsity
Conference paper
On quadratic convergence of DC proximal Newton algorithm in nonconvex sparse learning
Conference paper
Projection-free distributed online learning in networks
Conference paper
Projection-free distributed online learning in networks
Conference paper
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Article
Towards more efficient SPSD matrix approximation and CUR matrix decomposition
Article
Exact recovery of hard thresholding pursuit
Conference paper
Fast Component Pursuit for Large-scale Inverse Covariance Estimation
Conference paper
Conference paper
Learning Additive Exponential Family Graphical Models via ℓ_{2,1}-norm Regularized M-Estimation
Conference paper
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity
Conference paper
Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity
Conference paper
Stochastic Optimization with Importance Sampling for Regularized Loss Minimization
Conference paper
Supervised and semi-supervised text categorization using LSTM for region embeddings
Conference paper
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
Conference paper
Learning sparse low-threshold linear classifiers
Article
Adaptive stochastic alternating direction method of multipliers
Conference paper
Adaptive stochastic alternating direction method of multipliers
Conference paper
Crowd fraud detection in internet advertising
Conference paper
Effective use of word order for text categorization with convolutional neural networks
Conference paper
Local smoothness in variance reduced optimization
Conference paper
Quartz: Randomized dual coordinate ascent with arbitrary sampling
Conference paper
Semi-supervised convolutional neural networks for text categorization via region embedding
Conference paper
Stochastic optimization with importance sampling for regularized loss minimization
Conference paper
A proximal stochastic gradient method with progressive variance reduction
Article
Learning nonlinear functions using regularized greedy forest
Article
Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
Article
Partial Gaussian graphical model estimation
Article
Random Design Analysis of Ridge Regression
Article
A convergence rate analysis for LogitBoost, MART and their variant
Conference paper
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Conference paper
Communication-efficient distributed optimization using an approximate Newton-type method
Conference paper
Compressed counting meets compressed sensing
Conference paper
Efficient mini-batch training for stochastic optimization
Conference paper
Gradient hard thresholding pursuit for sparsity-constrained optimization
Conference paper
A Joint Matrix Completion and Filtering Model for Influenza Serological Data Integration
Article
A proximal-gradient homotopy method for the sparse least-squares problem
Article
Multi-stage convex relaxation for feature selection
Article
Stochastic Dual Coordinate Ascent methods for regularized loss minimization
Article
Truncated power method for sparse eigenvalue problems
Article
Accelerated mini-batch stochastic dual coordinate ascent
Conference paper
Accelerating stochastic gradient descent using predictive variance reduction
Conference paper
High-dimensional joint sparsity random effects model for multi-task learning
Conference paper
Conference paper
A General theory of concave regularization for high-dimensional sparse estimation problems
Article
A spectral algorithm for learning Hidden Markov Models
Article
A tail inequality for quadratic forms of subgaussian random vectors
Article
Deviation optimal learning using greedy q-aggregation
Article
Article
Tail inequalities for sums of random matrices that depend on the intrinsic dimension
Article
A proximal-gradient homotopy method for the ℓ 1-regularized least-squares problem
Conference paper
Random design analysis of ridge regression
Conference paper
Selective labeling via error bound minimization
Conference paper
Adaptive forward-backward greedy algorithm for learning sparse representations
Article
Concepts and applications for influenza antigenic cartography
Article
Integrative analysis of many weighted Co-Expression networks using tensor computation
Article
Learning with structured sparsity
Article
Robust matrix decomposition with sparse corruptions
Article
Sparse recovery with orthogonal matching pursuit under RIP
Article
Efficient optimal learning for contextual bandits
Conference paper
Conference paper
Learning to search efficiently in high dimensions
Conference paper
Spectral methods for learning multivariate latent tree structure
Conference paper
A computational framework for influenza antigenic cartography
Article
Analysis of multi-stage convex relaxation for sparse regularization
Article
Article
Trading accuracy for sparsity in optimization problems with sparsity constraints
Article
Fundamental statistical techniques
Book chapter
Agnostic active learning without constraints
Conference paper
Conference paper
Image classification using supervector coding of local image descriptors
Conference paper
Improved local coordinate coding using local tangents
Conference paper
Classifying search quries using the web as a source of knowledge.
Article
On the consistency of feature selection using greedy least squares regression
Article
Some sharp performance bounds for least squares regression with L_{1} regularization
Article
Sparse Online Learning via Truncated Gradient
Article
A spectral algorithm for learning hidden Markov models
Conference paper
Learning nonlinear dynamic models
Conference paper
Learning with structured sparsity
Conference paper
Multi-label prediction via compressed sensing
Conference paper
Nonlinear learning using local coordinate coding
Conference paper
An online relevant set algorithm for statistical machine translation
Article
Graph-based semi-supervised learning and spectral kernel design
Article
Statistical analysis of Bayes optimal subset ranking
Article
Adaptive forward-backward greedy algorithm for sparse learning with linear models
Conference paper
Multi-stage convex relaxation for learning with sparse regularization
Conference paper
Sparse online learning via truncated gradient
Conference paper
A block bigram prediction model for statistical machine translation
Article
On the effectiveness of Laplacian normalization for graph semi-supervised learning
Article
A general boosting method and its application to learning ranking functions for Web search
Conference paper
Epoch-Greedy algorithm for multi-armed bandits with side information
Conference paper
Conference paper
Robust classification of rare queries using web knowledge
Conference paper
Two-view feature generation model for semi-supervised learning
Conference paper
From ε-entropy to KL-entropy: Analysis of minimum information complexity density estimation
Article
Information theoretical upper and lower bounds for statistical estimation
Article
A discriminative global training algorithm for statistical MT
Conference paper
Learning on graph with Laplacian regularization
Conference paper
Linear prediction models with graph regularization for Web-page categorization
Conference paper
Subset ranking using regression
Conference paper
A framework for learning predictive structures from multiple tasks and unlabeled data
Article
Boosting with early stopping: Convergence and consistency
Article
Learning bounds for kernel regression using effective data dimensionality
Article
Text mining: Predictive methods for analyzing unstructured information
Book
A high-performance semi-supervised learning method for text chunking
Conference paper
A localized prediction model for statistical machine translation
Conference paper
Analysis of spectral kernel design based semi-supervised learning
Conference paper
Data dependent concentration bounds for sequential prediction algorithms
Conference paper
Localized upper and lower bounds for some estimation problems
Conference paper
TREC 2005 genomics track experiments at IBM watson
Conference paper
Greedy algorithms for classification - Consistency, convergence rates, and adaptivity
Article
Statistical analysis of some multi-category large margin classification methods
Article
Statistical behavior and consistency of classification methods based on convex risk minimization
Article
Text categorization for a comprehensive time-dependent benchmark
Article
An evaluation of over-the-counter medication sales for syndromic surveillance
Conference paper
An infinity-sample theory for multi-category large margin classification
Conference paper
Conference paper
Column-generation boosting methods for mixture of kernels
Conference paper
Focused named entity recognition using machine learning
Conference paper
Generalization error bounds for Bayesian mixture algorithms
Conference paper
Learning bounds for a generalized family of Bayesian posterior distributions
Conference paper
On the convergence of MDL density estimation
Conference paper
Solving large scale linear prediction problems using stochastic gradient descent algorithms
Conference paper
Support vector classification with input data uncertainty
Conference paper
Leave-one-out bounds for kernel methods
Article
Sequential greedy approximation for certain convex optimization problems
Article
Performance analysis and evaluation
Book chapter
A robust risk minimization based named entity recognition system
Conference paper
Data-dependent bounds for Bayesian mixture methods
Conference paper
Howtogetachinesename (entity): Segmentation and combination issues.
Conference paper
Named entity recogintion through classifier combination
Conference paper
On the Convergence of Boosting Procedures
Conference paper
Updating an nlp system to fit new domains: an empirical study on the sentence segmentation problem
Conference paper
A decision-tree-based symbolic rule induction system for text categorization
Article
Approximation bounds for some sparse kernel regression algorithms
Article
Covering Number Bounds of Certain Regularized Linear Function Classes
Article
On the consistency of instantaneous rigid motion estimation
Article
On the dual formulation of regularized linear systems
Article
Recommender Systems Using Linear Classifiers
Article
Text Chunking based on a Generalization of Winnow
Article
Two-Sided Arnoldi and Nonsymmetric Lanczos Algorithms
Article
Effective dimension and generalization of kernel learning
Conference paper
Generalization performance of some learning problems in hilbert functional spaces
Conference paper
Statistical behavior and consistency of support vector machines, boosting, and beyond
Conference paper
The consistency of greedy algorithms for classification
Conference paper
Rank-one approximation to high order tensors
Article
Text Categorization Based on Regularized Linear Classification Methods
Article
A general greedy approximation algorithm with applications
Conference paper
A leave-one-out cross validation bound for kernel methods with applications in learning
Conference paper
Conference paper
Convergence of large margin separable linear classification
Conference paper
Empirical study of recommender systems using linear classifiers
Conference paper
Conference paper
Some sparse approximation bounds for regression problems
Conference paper
Text chunking using regularized Winnow
Conference paper
Article
A probability analysis on the value of unlabeled data for classification problems
Conference paper
Active learning using adaptive resampling
Conference paper
Large margin Winnow methods for text categorization
Conference paper
Subspace iterative methods for eigenvalue problems
Article
Fast, robust, and consistent camera motion estimation
Conference paper
Some theoretical results concerning the convergence of composition of regularizated linear functions
Conference paper
Theoretical analysis of a class of randomized regularization methods
Conference paper
Eigenvalue perturbation and the generalized Krylov subspace method
Article
On the Homotopy Method for Perturbed Symmetric Generalized Eigenvalue Problems
Article
A linear algorithm for optimal context clustering with application to bi-level image coding
Conference paper
Compression by model combination
Conference paper
Model reduction for peec models including retardation
Conference paper
A progressive ziv-lempel algorithm for image compression
Conference paper
Progressive Ziv-Lempel Encoding of Synthetic Images
Conference paper
Optimal surface smoothing as filter design
Conference paper
Densities of self-similar measures on the line
Article
COMP4971A | Independent Work |
COMP6922F | Research Project |
MATH6911E | Reading Course: Recent Advances in Generative AI |
COMP4971A | Independent Work |
COMP6922F | Research Project |
UROP1100J | Undergraduate Research Opportunities Series 1 |
UROP2100J | Undergraduate Research Opportunities Series 2 |
COMP3711 | Design and Analysis of Algorithms |
COMP4981H | Final Year Thesis |
UROP1100I | Undergraduate Research Opportunities Series 1 |
COMP4981H | Final Year Thesis |
COMP6211E | Optimization for Machine Learning |
MATH6450J | Optimization for Machine Learning |
COMP4981H | Final Year Thesis |
No Teaching Assignments |
HAO, Yifan
Mathematics
HUANG, Xunpeng
(co-supervision)
Individualized Interdisciplinary Program (Artificial Intelligence)
SU, Ying
(co-supervision)
Individualized Interdisciplinary Program (Artificial Intelligence)
YANG, Rui
Computer Science and Engineering
YE, Chenlu
(co-supervision)
Individualized Interdisciplinary Program (Artificial Intelligence)
DIAO, Shizhe
Computer Science and Engineering
PI, Renjie
Computer Science and Engineering
ZHANG, Jipeng
Computer Science and Engineering
LIN, Yong
Computer Science and Engineering
PAN, Rui
Computer Science and Engineering
REN, Xiaozhe
(co-supervision)
Computer Science and Engineering
YAO, Lewei
(co-supervision)
Computer Science and Engineering
DONG, Hanze
Mathematics
LIAN, Qing
Computer Science and Engineering
ZHOU, Xiao
Computer Science and Engineering
SHUM, Ka Shun
Computer Science and Engineering
PAAT, Helbert Agluba
Computer Science and Engineering
HUANG, Zhichao
Mathematics( Completed in 2022 )
SHEN, Xinwei
Mathematics( Completed in 2022 )
YIU, Wai Keung Binnie
Computer Science and Engineering( Completed in 2022 )
DIAO, Shizhe
Computer Science and Engineering( Completed in 2021 )
DING, Yuhui
Computer Science and Engineering( Completed in 2021 )
HUANG, Yaowei
Computer Science and Engineering( Completed in 2021 )
Update your browser to view this website correctly. Update your browser now