Stochastic gradient descent without full data shuffle: with applications to in-database machine learning and deep learning systems

Article

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards

Conference paper

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Conference paper

Rewards-in-Context: Multi-Objective Alignment of Foundation Models with Dynamic Preference Adjustment

Conference paper

Gradient-Variation Bound for Online Convex Optimization with Constraints

Conference paper

Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics

Conference paper

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

Conference paper

Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning

Conference paper

In-Database Machine Learning with CorgiPile: Stochastic Gradient Descent without Full Data Shuffle

Conference paper

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Conference paper

Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions

Conference paper

Stylized Neural Painting

Conference paper

Robust one-bit recovery via relu generative networks: Near-optimal statistical rate and global landscape analysis

Conference paper

Upper confidence primal-dual reinforcement learning for CMDP with adversarial loss

Conference paper