Alert button
Picture for Chi Jin

Chi Jin

Alert button

Tuning-Free Stochastic Optimization

Feb 12, 2024
Ahmed Khaled, Chi Jin

Viaarxiv icon

Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift

Nov 27, 2023
Jiawei Ge, Shange Tang, Jianqing Fan, Cong Ma, Chi Jin

Viaarxiv icon

ZeroSwap: Data-driven Optimal Market Making in DeFi

Oct 13, 2023
Viraj Nadkarni, Jiachen Hu, Ranvir Rana, Chi Jin, Sanjeev Kulkarni, Pramod Viswanath

Viaarxiv icon

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

Sep 29, 2023
Zihan Ding, Chi Jin

Viaarxiv icon

Is RLHF More Difficult than Standard RL?

Jun 25, 2023
Yuanhao Wang, Qinghua Liu, Chi Jin

Figure 1 for Is RLHF More Difficult than Standard RL?
Viaarxiv icon

Context-lumpable stochastic bandits

Jun 22, 2023
Chung-Wei Lee, Qinghua Liu, Yasin Abbasi-Yadkori, Chi Jin, Tor Lattimore, Csaba Szepesvári

Viaarxiv icon

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

May 25, 2023
Ahmed Khaled, Konstantin Mishchenko, Chi Jin

Figure 1 for DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Figure 2 for DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Figure 3 for DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Figure 4 for DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Viaarxiv icon

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

May 18, 2023
Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári

Viaarxiv icon

Learning a Universal Human Prior for Dexterous Manipulation from Human Preference

Apr 10, 2023
Zihan Ding, Yuanpei Chen, Allen Z. Ren, Shixiang Shane Gu, Hao Dong, Chi Jin

Figure 1 for Learning a Universal Human Prior for Dexterous Manipulation from Human Preference
Figure 2 for Learning a Universal Human Prior for Dexterous Manipulation from Human Preference
Figure 3 for Learning a Universal Human Prior for Dexterous Manipulation from Human Preference
Figure 4 for Learning a Universal Human Prior for Dexterous Manipulation from Human Preference
Viaarxiv icon

On the Provable Advantage of Unsupervised Pretraining

Mar 02, 2023
Jiawei Ge, Shange Tang, Jianqing Fan, Chi Jin

Viaarxiv icon