activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Provable diffusion-based posterior sampling for linear inverse problems via DDIM

Yuchen Jiao, Na Li, Changxiao Cai +2

Diffusion-based methods have achieved remarkable empirical success in solving inverse problems. However, many existing posterior samplers either lack rigorous theoretical guarantee…

cs.LG2026

Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning

Bo Dai, Na Li, Dale Schuurmans

Self-supervised learning (SSL) has improved empirical performance by unleashing the power of unlabeled data for practical applications. Specifically, SSL extracts the representatio…

cs.LG2026

Spectral Representation-based Reinforcement Learning

Chenxiao Gao, Haotian Sun, Na Li +2

In real-world applications with large state and action spaces, reinforcement learning (RL) typically employs function approximations to represent core components like the policies,…

cs.LG2025

One-Step Flow Policy Mirror Descent

Tianyi Chen, Haitong Ma, Na Li +2

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models reli…

cs.LG2025

Efficient Online Reinforcement Learning for Diffusion Policy

Haitong Ma, Tianyi Chen, Kai Wang +2

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diff…

cs.LG2024

Primal-Dual Spectral Representation for Off-policy Evaluation

Yang Hu, Tianyi Chen, Na Li +2

Off-policy evaluation (OPE) is one of the most fundamental problems in reinforcement learning (RL) to estimate the expected long-term payoff of a given target policy with only expe…