activity
20082023
most citedSever: A Robust Meta-Algorithm for Stochastic Optimization

142 citations · 752 across the 110 of their papers we have counts for

collaborators
Showing 2020Show all

16 papers · 1 filter

cs.LG2020★ 1 cited

The Sample Complexity of Robust Covariance Testing

Ilias Diakonikolas, Daniel M. Kane

We study the problem of testing the covariance matrix of a high-dimensional Gaussian in a robust setting, where the input distribution has been corrupted in Huber's contamination m…

cs.LG2020

Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models

Ilias Diakonikolas, Daniel M. Kane

Let be any vector space of multivariate degree- homogeneous polynomials with co-dimension at most , and be the set of points where all polynomials in {\em nearly}…

cs.LG2020

Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise

Ilias Diakonikolas, Daniel M. Kane

We study the problem of PAC learning halfspaces with Massart noise. Given labeled samples from a distribution on such that the margi…

cs.DS2020★ 4 cited

List-Decodable Mean Estimation in Nearly-PCA Time

Ilias Diakonikolas, Daniel M. Kane, Daniel Kongsgaard +2

Traditionally, robust statistics has focused on designing estimators tolerant to a minority of contaminated data. Robust list-decodable learning focuses on the more challenging reg…

cs.LG2020★ 9 cited

A Polynomial Time Algorithm for Learning Halfspaces with Tsybakov Noise

Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis +2

We study the problem of PAC learning homogeneous halfspaces in the presence of Tsybakov noise. In the Tsybakov noise model, the label of every sample is independently flipped with…

cs.DC2020

Prisoners, Rooms, and Lightswitches

Daniel M. Kane, Scott Duke Kominers

We examine a new variant of the classic prisoners and lightswitches puzzle: A warden leads his prisoners in and out of rooms, one at a time, in some order, with each prison…