activity
20092022
most citedTheory of Deep Learning IIb: Optimization Properties of SGD

44 citations · 142 across the 15 of their papers we have counts for

collaborators
Showing math.STShow all

7 papers · 1 filter

math.ST2021

Deep learning: a statistical viewpoint

Peter L. Bartlett, Andrea Montanari, Alexander Rakhlin

The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal…

math.ST2021

On the Minimal Error of Empirical Risk Minimization

Gil Kur, Alexander Rakhlin

We study the minimal error of the Empirical Risk Minimization (ERM) procedure in the task of regression, both in the random and the fixed design settings. Our sharp lower bounds sh…

math.ST20203 cited

On Suboptimality of Least Squares with Application to Estimation of Convex Bodies

Gil Kur, Alexander Rakhlin, Adityanand Guntuboyina

We develop a technique for establishing lower bounds on the sample complexity of Least Squares (or, Empirical Risk Minimization) for large classes of functions. As an application,…

math.ST2019

On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels

Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai

We study the risk of minimum-norm interpolants of data in Reproducing Kernel Hilbert Spaces. Our upper bounds on the risk are of a multiple-descent shape for the various scalings o…

math.ST2019

Optimality of Maximum Likelihood for Log-Concave Density Estimation and Bounded Convex Regression

Gil Kur, Yuval Dagan, Alexander Rakhlin

In this paper, we study two problems: (1) estimation of a -dimensional log-concave distribution and (2) bounded multivariate convex regression with random design with an underly…

math.ST2018

Just Interpolate: Kernel "Ridgeless" Regression Can Generalize

Tengyuan Liang, Alexander Rakhlin

In the absence of explicit regularization, Kernel "Ridgeless" Regression with nonlinear kernels has the potential to fit the training data perfectly. It has been observed empirical…