The standard supervised learning paradigm works effectively when training data shares the
same distribution as the upcoming testing samples. However, this stationary assumption is …

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 …

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 …

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 …

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 …

Abstract We investigate online Markov Decision Processes (MDPs) with adversarially
changing loss functions and known transitions. We choose dynamic regret as the …

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 …