activity
20112026
most citedGlobal Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Minimax Problems

33 citations · 107 across the 19 of their papers we have counts for

collaborators
Showing cs.ITShow all

6 papers · 1 filter

cs.IT2023

Gaussian Database Alignment and Gaussian Planted Matching

Osman Emre Dai, Daniel Cullina, Negar Kiyavash

Database alignment is a variant of the graph alignment problem: Given a pair of anonymized databases containing separate yet correlated features for a set of users, the problem is…

cs.IT2018

Fundamental Limits of Database Alignment

Daniel Cullina, Prateek Mittal, Negar Kiyavash

We consider the problem of aligning a pair of databases with correlated entries. We introduce a new measure of correlation in a joint distribution that we call cycle mutual informa…

cs.IT20153 cited

Bounded Degree Approximations of Stochastic Networks

Christopher J. Quinn, Ali Pinar, Negar Kiyavash

We propose algorithms to approximate directed information graphs. Directed information graphs are probabilistic graphical models that depict causal dependencies between stochastic…

cs.IT20121 cited

Two Approaches to the Construction of Deletion Correcting Codes: Weight Partitioning and Optimal Colorings

Daniel Cullina, Ankur A. Kulkarni, Negar Kiyavash

We consider the problem of constructing deletion correcting codes over a binary alphabet and take a graph theoretic view. An -bit -deletion correcting code is an independent…

cs.IT2012

Non-asymptotic Upper Bounds for Deletion Correcting Codes

Ankur A. Kulkarni, Negar Kiyavash

Explicit non-asymptotic upper bounds on the sizes of multiple-deletion correcting codes are presented. In particular, the largest single-deletion correcting code for -ary alphab…

cs.IT20116 cited

Causal Dependence Tree Approximations of Joint Distributions for Multiple Random Processes

Christopher J. Quinn, Todd P. Coleman, Negar Kiyavash

We investigate approximating joint distributions of random processes with causal dependence tree distributions. Such distributions are particularly useful in providing parsimonious…