activity
20052026
most citedThe Robust Manifold Defense: Adversarial Training using Generative Models

116 citations · 1.1k across the 89 of their papers we have counts for

collaborators
Showing 2016Show all

5 papers · 1 filter

cs.LG2016★ 14 cited

Square Hellinger Subadditivity for Bayesian Networks and its Applications to Identity Testing

Constantinos Daskalakis, Qinxuan Pan

We show that the square Hellinger distance between two Bayesian networks on the same directed graph, , is subadditive with respect to the neighborhoods of . Namely, if an…

cs.DS2016

Testing Ising Models

Constantinos Daskalakis, Nishanth Dikkala, Gautam Kamath

Given samples from an unknown multivariate distribution , is it possible to distinguish whether is the product of its marginals versus being far from every product distr…

stat.ML2016★ 28 cited

Ten Steps of EM Suffice for Mixtures of Two Gaussians

Constantinos Daskalakis, Christos Tzamos, Manolis Zampetakis

The Expectation-Maximization (EM) algorithm is a widely used method for maximum likelihood estimation in models with latent variables. For estimating mixtures of Gaussians, its ite…

cs.GT2016

Revenue Maximization and Ex-Post Budget Constraints

Constantinos Daskalakis, Nikhil R. Devanur, S. Matthew Weinberg

We consider the problem of a revenue-maximizing seller with m items for sale to n additive bidders with hard budget constraints, assuming that the seller has some prior distributio…

cs.GT2016★ 1 cited

Sequential Mechanisms with ex-post Participation Guarantees

Itai Ashlagi, Constantinos Daskalakis, Nima Haghpanah

We provide a characterization of revenue-optimal dynamic mechanisms in settings where a monopolist sells k items over k periods to a buyer who realizes his value for item i in the…