10 citations · 21 across the 40 of their papers we have counts for
5 papers · 1 filter
Reliable Replay through Spatial Coherence in Online Continual Learning
Haixiang Sun, Jiefu Zhang, Yinghao He +4
Continually adapting models to new tasks requires retaining earlier knowledge under limited memory and computation. Experience replay addresses this challenge, but priorities based…
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
Yang Xu, Jiefu Zhang, Haixiang Sun +3
Adaptive prompt and program search makes LLM evaluation selection-sensitive. Once benchmark items are reused inside tuning, the observed winner's score need not estimate the fresh-…
Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients
Yang Xu, Vaneet Aggarwal
We study fixed-policy evaluation for finite Markov chains that may be reducible and periodic. Classical evaluation methods with gain and bias decomposition are not always diagnosti…
Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning
Yang Xu, Washim Uddin Mondal, Vaneet Aggarwal
We present the first finite-sample analysis of policy evaluation in robust average-reward Markov Decision Processes (MDPs). Prior work in this setting have established only asympto…
Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
Ahmadreza Moradipari, Mohammad Pedramfar, Modjtaba Shokrian Zini +1
In this paper, we prove the first Bayesian regret bounds for Thompson Sampling in reinforcement learning in a multitude of settings. We simplify the learning problem using a discre…