activity
20182024
most citedBlack-box Adversarial Attacks with Bayesian Optimization

25 citations · 63 across the 10 of their papers we have counts for

collaborators
Showing math.OCShow all

7 papers · 1 filter

math.OC2022

Nonlinear gradient mappings and stochastic optimization: A general framework with applications to heavy-tail noise

Dusan Jakovetic, Dragana Bajovic, Anit Kumar Sahu +3

We introduce a general framework for nonlinear stochastic gradient descent (SGD) for the scenarios when gradient noise exhibits heavy tails. The proposed framework subsumes several…

math.OC2018

Towards Gradient Free and Projection Free Stochastic Optimization

Anit Kumar Sahu, Manzil Zaheer, Soummya Kar

This paper focuses on the problem of \emph{constrained} \emph{stochastic} optimization. A zeroth order Frank-Wolfe algorithm is proposed, which in addition to the projection-free n…

math.OC2018

Communication-Efficient Distributed Strongly Convex Stochastic Optimization: Non-Asymptotic Rates

Anit Kumar Sahu, Dusan Jakovetic, Dragana Bajovic +1

We examine fundamental tradeoffs in iterative distributed zeroth and first order stochastic optimization in multi-agent networks in terms of \emph{communication cost} (number of pe…

math.OC2018

Distributed Zeroth Order Optimization Over Random Networks: A Kiefer-Wolfowitz Stochastic Approximation Approach

Anit Kumar Sahu, Dusan Jakovetic, Dragana Bajovic +1

We study a standard distributed optimization framework where networked nodes collaboratively minimize the sum of their local convex costs. The main body of existing work consid…

math.OC2018

Convergence rates for distributed stochastic optimization over random networks

Dusan Jakovetic, Dragana Bajovic, Anit Kumar Sahu +1

We establish the O() convergence rate for distributed stochastic gradient methods that operate over strongly convex costs and random networks. The considered class of…

math.OC2018

: A Distributed Random Fields Estimator

Anit Kumar Sahu, Dusan Jakovetic, Soummya Kar

This paper presents a communication efficient distributed algorithm, of the \emph{consensus}+\emph{innovations} type, to estimate a high-dimensional parameter in…