3 citations · 6 across the 21 of their papers we have counts for
8 papers · 1 filter
High-Dimensional Gaussian Mean Estimation under Realizable Contamination
Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas
We study mean estimation for a Gaussian distribution with identity covariance in under a missing data scheme termed realizable -contamination model. In this model…
On Learning Parallel Pancakes with Mostly Uniform Weights
Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar +2
We study the complexity of learning -mixtures of Gaussians (-GMMs) on . This task is known to have complexity in full generality. To circumvent this…
Batch List-Decodable Linear Regression via Higher Moments
Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar +2
We study the task of list-decodable linear regression using batches. A batch is called clean if it consists of i.i.d. samples from an unknown linear regression distribution. For a…
Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination
Ilias Diakonikolas, Daniel M. Kane, Sushrut Karmalkar +2
We study Gaussian sparse estimation tasks in Huber's contamination model with a focus on mean estimation, PCA, and linear regression. For each of these tasks, we give the first sam…
Clustering Mixtures of Bounded Covariance Distributions Under Optimal Separation
Ilias Diakonikolas, Daniel M. Kane, Jasper C. H. Lee +1
We study the clustering problem for mixtures of bounded covariance distributions, under a fine-grained separation assumption. Specifically, given samples from a -component mixtu…
SQ Lower Bounds for Learning Bounded Covariance GMMs
Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas +1
We study the complexity of learning mixtures of separated Gaussians with common unknown bounded covariance matrix. Specifically, we focus on learning Gaussian mixture models (GMMs)…
Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
Ilias Diakonikolas, Daniel M. Kane, Ankit Pensia +1
We study principal component analysis (PCA), where given a dataset in from a distribution, the task is to find a unit vector that approximately maximizes the var…
The Optimality of Polynomial Regression for Agnostic Learning under Gaussian Marginals
Ilias Diakonikolas, Daniel M. Kane, Thanasis Pittas +1
We study the problem of agnostic learning under the Gaussian distribution. We develop a method for finding hard families of examples for a wide class of problems by using LP dualit…