Robust statistics is the study of designing estimators that perform well even when the dataset
significantly deviates from the idealized modeling assumptions, such as in the presence of …

We study the problem of learning a local quantum Hamiltonian H given copies of its Gibbs
state ρ= e− β H/(e− β H) at a known inverse temperature β> 0. Anshu, Arunachalam …

Inference problems with conjectured statistical-computational gaps are ubiquitous
throughout modern statistics, computer science, statistical physics and discrete probability …

In statistical learning and analysis from shared data, which is increasingly widely adopted in
platforms such as federated learning and meta-learning, there are two major concerns …

We study the problem of private distribution learning with access to public data. In this setup,
which we refer to as* public-private learning*, the learner is given public and private …

We give the first polynomial time and sample (epsilon, delta)-differentially private (DP)
algorithm to estimate the mean, covariance and higher moments in the presence of a …

We give a polynomial-time algorithm for the problem of robustly estimating a mixture of k
arbitrary Gaussians in ℝ d, for any fixed k, in the presence of a constant fraction of arbitrary …

List-decodable Linear Regression Page 1 List-decodeable Linear Regression Sushrut
Karmalkar University of Texas at Austin sushrutk@cs.utexas.edu Adam R. Klivans University of …

We give the first tester-learner for halfspaces that succeeds universally over a wide class of
structured distributions. Our universal tester-learner runs in fully polynomial time and has the …

We obtain robust and computationally efficient estimators for learning several linear models
that achieve statistically optimal convergence rate under minimal distributional assumptions …