• Publications
  • Influence
Federated Optimization in Heterogeneous Networks
We propose FedProx, a federated optimization algorithm that addresses the challenges of heterogeneity in federated networks. Expand
Federated Learning: Challenges, Methods, and Future Directions
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Expand
On the Convergence of Federated Optimization in Heterogeneous Networks
We propose and introduce \fedprox, which is similar in spirit to \fedavg, but more amenable to theoretical analysis. Expand
Distributed Sequential Detection for Gaussian Shift-in-Mean Hypothesis Testing
  • Anit Kumar Sahu, S. Kar
  • Mathematics, Computer Science
  • IEEE Transactions on Signal Processing
  • 27 November 2014
This paper studies the problem of sequential Gaussian shift-in-mean hypothesis testing in a distributed multi-agent network. Expand
Distributed stochastic optimization with gradient tracking over strongly-connected networks
We study distributed stochastic optimization to minimize a sum of smooth and strongly-convex local cost functions over a network of agents, communicating over a strongly-connected graph. Expand
MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling
A novel algorithm MATCHA uses matching decomposition sampling of the base topology to parallelize inter-worker information exchange so as to significantly reduce communication delay. Expand
Distributed Zeroth Order Optimization Over Random Networks: A Kiefer-Wolfowitz Stochastic Approximation Approach
In this paper, we consider the currently understudied but highly relevant scenarios when: 1) only noisy function values' estimates are available (no gradients nor Hessians can be evaluated). Expand
Towards Gradient Free and Projection Free Stochastic Optimization
A zeroth order Frank-Wolfe algorithm that converges to the optimal objective function at a rate $O(1/T^{1/3}T^{-1/4}\right)$, where $T$ denotes the iteration count. Expand
$\mathcal {CIRFE}$: A Distributed Random Fields Estimator
The paper presents a communication efficient distributed algorithm, <inline-formula><tex-math notation="LaTeX"> $\mathcal {CIRFE}$</tex-Math></inline- formula>, to estimate a high-dimensional parameter in a multi-agent network, in which each agent is interested in reconstructing only a few components of the parameter. Expand
Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output labels (hard label) to a queried data input. Expand