We consider the setting of online linear regression for arbitrary deterministic sequences, with
the square loss. We are interested in the aim set by Bartlett et al.(2015): obtain regret …

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 …

In statistical learning theory, determining the sample complexity of realizable binary
classification for VC classes was a long-standing open problem. The results of Simon [1] and …

This article proposes an alternative to the Hosmer-Lemeshow (HL) test for evaluating the
calibration of probability forecasts for binary events. The approach is based on e-values, a …

We consider the problem of estimating piecewise regular functions in an online setting, ie,
the data arrive sequentially and at any round our task is to predict the value of the true …

This document contains lecture notes for a course titled 'Introduction to Online Learning”
which I taught in Fall 2022. These notes borrow material from several sources. The …

Rapid development of data science technologies have enabled data-driven algorithms for
many important operational problems. Existing data-driven solutions often requires the …

An approximation to discrete noisy data is constructed that obtains monotonicity. Precisely,
we address the problem of making the least sum of 4th powers change to the data that …

Ce travail présente quelques contributions théoriques et pratiques à la prévision des suites
arbitraires. Dans ce domaine, la prévision se déroule séquentiellement en même temps que …