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 …

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

It is often observed that the probabilistic predictions given by a machine learning model can
disagree with averaged actual outcomes on specific subsets of data, which is also known as …

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 the problem of estimating a function from $ n $ noisy samples whose discrete
Total Variation (TV) is bounded by $ C_n $. We reveal a deep connection to the seemingly …

In this paper, we consider the problem of differentially private (DP) algorithms for isotonic
regression. For the most general problem of isotonic regression over a partially ordered set …

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

Motivated by our collaboration with Anheuser-Busch InBev (AB InBev), a consumer
packaged goods (CPG) company, we consider the problem of forecasting sales under the …