4 papers · 1 filter
Optimal Multi-Distribution Learning
Zihan Zhang, Wenhao Zhan, Yuxin Chen +2
Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across distinct data distributions, has emerged as a unified framework…
Anytime Acceleration of Gradient Descent
Zihan Zhang, Jason D. Lee, Simon S. Du +1
This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsi…
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Kaifeng Lyu, Jikai Jin, Zhiyuan Li +3
Recent work by Power et al. (2022) highlighted a surprising "grokking" phenomenon in learning arithmetic tasks: a neural net first "memorizes" the training set, resulting in perfec…
Horizon-Free Regret for Linear Markov Decision Processes
Zihan Zhang, Jason D. Lee, Yuxin Chen +1
A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a.k.a.~the horizon-free bounds. However, these regret bo…