activity
20052022
most citedSpectrally-normalized margin bounds for neural networks

174 citations · 612 across the 29 of their papers we have counts for

collaborators
Showing stat.MLShow all

18 papers · 1 filter

stat.ML2021

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?

Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett

We establish conditions under which gradient descent applied to fixed-width deep networks drives the logistic loss to zero, and prove bounds on the rate of convergence. Our analysi…

stat.ML2020

When does gradient descent with logistic loss find interpolating two-layer networks?

Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett

We study the training of finite-width two-layer smoothed ReLU networks for binary classification using the logistic loss. We show that gradient descent drives the training loss to…

stat.ML2020

Failures of model-dependent generalization bounds for least-norm interpolation

Peter L. Bartlett, Philip M. Long

We consider bounds on the generalization performance of the least-norm linear regressor, in the over-parameterized regime where it can interpolate the data. We describe a sense in…

stat.ML202013 cited

Optimal Robust Linear Regression in Nearly Linear Time

Yeshwanth Cherapanamjeri, Efe Aras, Nilesh Tripuraneni +3

We study the problem of high-dimensional robust linear regression where a learner is given access to samples from the generative model (with $X…

stat.ML202021 cited

On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration

Wenlong Mou, Chris Junchi Li, Martin J. Wainwright +2

We undertake a precise study of the asymptotic and non-asymptotic properties of stochastic approximation procedures with Polyak-Ruppert averaging for solving a linear system $\bar{…

stat.ML20191 cited

Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing

Wenlong Mou, Nhat Ho, Martin J. Wainwright +2

We study the problem of sampling from the power posterior distribution in Bayesian Gaussian mixture models, a robust version of the classical posterior. This power posterior is kno…