In the eyes of many control scientists, the theory of the scenario approach is a tool for
determining the sample size in certain randomized control-design methods, where an …

We study square loss in a realizable time-series framework with martingale difference noise.
Our main result is a fast rate excess risk bound which shows that whenever a trajectory …

Graph-based machine learning is experiencing explosive growth, driven by impressive
recent developments and wide applicability. Typical approaches for graph representation …

Given samples from an unknown multivariate distribution p, is it possible to distinguish
whether p is the product of its marginals versus p being far from every product distribution …

We study the problem of least squares linear regression where the datapoints are
dependent and are sampled from a Markov chain. We establish sharp information theoretic …

We initiate a study of supervised learning from many independent sequences (" trajectories")
of non-independent covariates, reflecting tasks in sequence modeling, control, and …

In this work, we establish risk bounds for Empirical Risk Minimization (ERM) with both
dependent and heavy-tailed data-generating processes. We do so by extending the seminal …

The vast majority of the work on adaptive data analysis focuses on the case where the
samples in the dataset are independent. Several approaches and tools have been …

We study stochastic optimization algorithms for constrained nonconvex stochastic
optimization problems with Markovian data. In particular, we focus on the case when the …

Generating unlabeled data has been recently shown to help address the few-shot
hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target …