A Saha, A Krishnamurthy - International Conference on …, 2022 - proceedings.mlr.press
We study the $ K $-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only …
P Zhao, YF Xie, L Zhang… - Advances in Neural …, 2022 - proceedings.neurips.cc
Non-stationary online learning has drawn much attention in recent years. In particular,\emph {dynamic regret} and\emph {adaptive regret} are proposed as two principled performance …
We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative …
D Baby, YX Wang - International Conference on Artificial …, 2022 - proceedings.mlr.press
We study the framework of universal dynamic regret minimization with strongly convex losses. We answer an open problem in Baby and Wang 2021 by showing that in a proper …
LF Li, P Zhao, ZH Zhou - Advances in Neural Information …, 2024 - proceedings.neurips.cc
We study reinforcement learning in episodic inhomogeneous MDPs with adversarial full- information rewards and the unknown transition kernel. We consider the linear mixture …
We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning …
Dealing with distribution shifts is one of the central challenges for modern machine learning. One fundamental situation is the covariate shift, where the input distributions of data change …
P Zhao, LF Li, ZH Zhou - International Conference on …, 2022 - proceedings.mlr.press
Abstract We investigate online Markov Decision Processes (MDPs) with adversarially changing loss functions and known transitions. We choose dynamic regret as the …
Z Zhang, A Cutkosky… - Advances in Neural …, 2024 - proceedings.neurips.cc
Motivated by the challenge of nonstationarity in sequential decision making, we study Online Convex Optimization (OCO) under the coupling of two problem structures: the domain is …