5 papers
Continuous-Time Analysis for Minimax and Bilevel Problems
Hyunwoo Lee, Jeongyeol Kwon, Dohyun Kwon
We study single-loop gradient-flow dynamics for nested optimization, where the outer variable evolves while auxiliary variables track the inner solution map. While existing analyse…
Optimal Zeroth-Order Bilevel Optimization
Alireza Aghasi, Jeongyeol Kwon, Saeed Ghadimi
In this paper, we develop zeroth-order algorithms with provably (nearly) optimal sample complexity for stochastic bilevel optimization, where only noisy function evaluations are av…
Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing
J. Jon Ryu, Jeongyeol Kwon, Benjamin Koppe +1
We consider off-policy selection and learning in contextual bandits, where the learner aims to select or train a reward-maximizing policy using data collected by a fixed behavior p…
An Empirical Study on the Power of Future Prediction in Partially Observable Environments
Jeongyeol Kwon, Liu Yang, Robert Nowak +1
Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxili…
Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way
Jeongyeol Kwon, Luke Dotson, Yudong Chen +1
Previous studies on two-timescale stochastic approximation (SA) mainly focused on bounding mean-squared errors under diminishing stepsize schemes. In this work, we investigate {\it…