no code implementations • 1 Jan 2014 • Shahar Mendelson
We obtain sharp bounds on the performance of Empirical Risk Minimization performed in a convex class and with respect to the squared loss, without assuming that class members and the target are bounded functions or have rapidly decaying tails.
no code implementations • 13 Oct 2014 • Shahar Mendelson
We study prediction and estimation problems using empirical risk minimization, relative to a general convex loss function.
no code implementations • 25 Feb 2015 • Shahar Mendelson
We introduce an alternative to the notion of `fast rate' in Learning Theory, which coincides with the optimal error rate when the given class happens to be convex and regular in some sense.
no code implementations • 9 Apr 2015 • Shahar Mendelson
We show that if $F$ is a convex class of functions that is $L$-subgaussian, the error rate of learning problems generated by independent noise is equivalent to a fixed point determined by `local' covering estimates of the class, rather than by the gaussian averages.
no code implementations • 15 Jan 2017 • Gábor Lugosi, Shahar Mendelson
A regularized risk minimization procedure for regression function estimation is introduced that achieves near optimal accuracy and confidence under general conditions, including heavy-tailed predictor and response variables.
no code implementations • 1 Feb 2017 • Gábor Lugosi, Shahar Mendelson
We study the problem of estimating the mean of a random vector $X$ given a sample of $N$ independent, identically distributed points.
no code implementations • 21 Feb 2017 • Shahar Mendelson
In this note we answer a question of G. Lecu\'{e}, by showing that column normalization of a random matrix with iid entries need not lead to good sparse recovery properties, even if the generating random variable has a reasonable moment growth.
no code implementations • 17 Jul 2017 • Shahar Mendelson
We study learning problems involving arbitrary classes of functions $F$, distributions $X$ and targets $Y$.
no code implementations • 4 Sep 2017 • Shahar Mendelson
The small-ball method was introduced as a way of obtaining a high probability, isomorphic lower bound on the quadratic empirical process, under weak assumptions on the indexing class.
no code implementations • 15 Apr 2018 • Shahar Mendelson
The slabs are generated using $X_1,..., X_N$, and under minimal assumptions on $X$ (e. g., $X$ can be heavy-tailed) it suffices that $N = c_1d \eta^{-4}\log(2/\eta)$ to ensure that $(1-\eta) {\cal K} \subset {\cal B} \subset (1+\eta){\cal K}$.
no code implementations • 10 Jun 2019 • Gabor Lugosi, Shahar Mendelson
We dedicate a section on statistical learning problems--in particular, regression function estimation--in the presence of possibly heavy-tailed data.
no code implementations • 4 Feb 2020 • Shahar Mendelson
We study learning problems in which the underlying class is a bounded subset of $L_p$ and the target $Y$ belongs to $L_p$.
no code implementations • 22 Oct 2020 • Gabor Lugosi, Shahar Mendelson
We consider the problem of estimating the mean of a random vector based on $N$ independent, identically distributed observations.
no code implementations • 3 Jul 2023 • Afonso S. Bandeira, Antoine Maillard, Shahar Mendelson, Elliot Paquette
We consider the problem $(\mathrm{P})$ of fitting $n$ standard Gaussian random vectors in $\mathbb{R}^d$ to the boundary of a centered ellipsoid, as $n, d \to \infty$.