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 2011Show all

9 papers · 1 filter

cs.DS2011★ 49 cited

Testing -Modal Distributions: Optimal Algorithms via Reductions

Constantinos Daskalakis, Ilias Diakonikolas, Rocco A. Servedio +2

We give highly efficient algorithms, and almost matching lower bounds, for a range of basic statistical problems that involve testing and estimating the L_1 distance between two k-…

cs.GT2011★ 14 cited

On Optimal Multi-Dimensional Mechanism Design

Constantinos Daskalakis, S. Matthew Weinberg

We efficiently solve the optimal multi-dimensional mechanism design problem for independent bidders with arbitrary demand constraints when either the number of bidders is a constan…

cs.GT2011★ 1 cited

A Constructive Approach to Reduced-Form Auctions with Applications to Multi-Item Mechanism Design

Yang Cai, Constantinos Daskalakis, S. Matthew Weinberg

We provide a constructive proof of Border's theorem [Bor91, HR15a] and its generalization to reduced-form auctions with asymmetric bidders [Bor07, MV10, CKM13]. Given a reduced for…

math.PR2011★ 15 cited

Alignment-free phylogenetic reconstruction: Sample complexity via a branching process analysis

Constantinos Daskalakis, Sebastien Roch

We present an efficient phylogenetic reconstruction algorithm allowing insertions and deletions which provably achieves a sequence-length requirement (or sample complexity) growing…

cs.DS2011★ 2 cited

Learning Poisson Binomial Distributions

Constantinos Daskalakis, Ilias Diakonikolas, Rocco A. Servedio

We consider a basic problem in unsupervised learning: learning an unknown \emph{Poisson Binomial Distribution}. A Poisson Binomial Distribution (PBD) over is the…

cs.DS2011

Learning -Modal Distributions via Testing

Constantinos Daskalakis, Ilias Diakonikolas, Rocco A. Servedio

A -modal probability distribution over the discrete domain is one whose histogram has at most "peaks" and "valleys." Such distributions are natural generalizat…