4 papers · 1 filter
Optimal e-value testing for properly constrained hypotheses
Eugenio Clerico
Hypothesis testing via e-variables can be framed as a sequential betting game, where a player each round picks an e-variable. A good player's strategy results in an effective stati…
On the optimality of coin-betting for mean estimation
Eugenio Clerico
We consider the problem of testing the mean of a bounded real random variable. We introduce a notion of optimal classes for e-variables and e-processes, and establish the optimalit…
Online-to-PAC generalization bounds under graph-mixing dependencies
Baptiste Abélès, Eugenio Clerico, Gergely Neu
Traditional generalization results in statistical learning require a training data set made of independently drawn examples. Most of the recent efforts to relax this independence a…
Generalization bounds for mixing processes via delayed online-to-PAC conversions
Baptiste Abeles, Eugenio Clerico, Gergely Neu
We study the generalization error of statistical learning algorithms in a non-i.i.d. setting, where the training data is sampled from a stationary mixing process. We develop an ana…