142 citations · 338 across the 19 of their papers we have counts for
7 papers · 1 filter
Testing Bayesian Networks
Clement Canonne, Ilias Diakonikolas, Daniel Kane +1
This work initiates a systematic investigation of testing high-dimensional structured distributions by focusing on testing Bayesian networks -- the prototypical family of directed…
Statistical Query Lower Bounds for Robust Estimation of High-dimensional Gaussians and Gaussian Mixtures
Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
We describe a general technique that yields the first {\em Statistical Query lower bounds} for a range of fundamental high-dimensional learning problems involving Gaussian distribu…
Playing Anonymous Games using Simple Strategies
Yu Cheng, Ilias Diakonikolas, Alistair Stewart
We investigate the complexity of computing approximate Nash equilibria in anonymous games. Our main algorithmic result is the following: For any -player anonymous game with a bo…
Efficient Robust Proper Learning of Log-concave Distributions
Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
We study the {\em robust proper learning} of univariate log-concave distributions (over continuous and discrete domains). Given a set of samples drawn from an unknown target distri…
Robust Learning of Fixed-Structure Bayesian Networks
Yu Cheng, Ilias Diakonikolas, Daniel Kane +1
We investigate the problem of learning Bayesian networks in a robust model where an -fraction of the samples are adversarially corrupted. In this work, we study the fully observ…
Learning Multivariate Log-concave Distributions
Ilias Diakonikolas, Daniel M. Kane, Alistair Stewart
We study the problem of estimating multivariate log-concave probability density functions. We prove the first sample complexity upper bound for learning log-concave densities on $\…
Robust Estimators in High Dimensions without the Computational Intractability
Ilias Diakonikolas, Gautam Kamath, Daniel Kane +3
We study high-dimensional distribution learning in an agnostic setting where an adversary is allowed to arbitrarily corrupt an -fraction of the samples. Such questions…