We consider the problem of the Zinkevich (2003)-style dynamic regret minimization in online
learning with\emph {exp-concave} losses. We show that whenever improper learning is …

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 …

Many settings involve sequential decision making where a set of actions can be chosen at
each time step, each action provides a stochastic reward, and the distribution for the reward …

This paper focuses on supervised and unsupervised online label shift, where the class
marginals $ Q (y) $ variesbut the class-conditionals $ Q (x| y) $ remain invariant. In the …

We present a series of theoretical and algorithmic results combining the benefits of the
statistical learning approach to time series prediction with that of on-line learning. We prove …

We consider the problem of online forecasting of sequences of length $ n $ with total-
variation at most $ C_n $ using observations contaminated by independent $\sigma …

We consider the framework of non-stationary stochastic optimization [Besbes et. al. 2015]
with squared error losses and noisy gradient feedback where the dynamic regret of an …

We consider online forecasting problems for non-convex machine learning models.
Forecasting introduces several challenges such as (i) frequent updates are necessary to …

We consider the problem of universal dynamic regret minimization under exp-concave and
smooth losses. We show that appropriately designed Strongly Adaptive algorithms achieve …

We consider the problem of forecasting a high-dimensional time series that can be modeled
as matrices where each column denotes a measurement and use low-rank matrix …