32 citations · 37 across the 10 of their papers we have counts for
11 papers
Abstract Operations Research Modeling Using Natural Language Inputs
Junxuan Li, Ryan Wickman, Sahil Bhatnagar +2
Operations research (OR) uses mathematical models to enhance decision-making, but developing these models requires expert knowledge and can be time-consuming. Automated mathematica…
Escaping Saddle Points in Distributed Newton's Method with Communication Efficiency and Byzantine Resilience
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar +1
The problem of saddle-point avoidance for non-convex optimization is quite challenging in large scale distributed learning frameworks, such as Federated Learning, especially in the…
Estimation of Shortest Path Covariance Matrices
Raj Kumar Maity, Cameron Musco
We study the sample complexity of estimating the covariance matrix of a distribution over given independent sample…
Distributed Newton Can Communicate Less and Resist Byzantine Workers
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar
We develop a distributed second order optimization algorithm that is communication-efficient as well as robust against Byzantine failures of the worker machines. We propose COMRADE…
A workload-adaptive mechanism for linear queries under local differential privacy
Ryan McKenna, Raj Kumar Maity, Arya Mazumdar +1
We propose a new mechanism to accurately answer a user-provided set of linear counting queries under local differential privacy (LDP). Given a set of linear counting queries (the w…
Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedback
Avishek Ghosh, Raj Kumar Maity, Swanand Kadhe +2
We develop a communication-efficient distributed learning algorithm that is robust against Byzantine worker machines. We propose and analyze a distributed gradient-descent algorith…
vqSGD: Vector Quantized Stochastic Gradient Descent
Venkata Gandikota, Daniel Kane, Raj Kumar Maity +1
In this work, we present a family of vector quantization schemes \emph{vqSGD} (Vector-Quantized Stochastic Gradient Descent) that provide an asymptotic reduction in the communicati…
High Dimensional Discrete Integration over the Hypergrid
Raj Kumar Maity, Arya Mazumdar, Soumyabrata Pal
Recently Ermon et al. (2013) pioneered a way to practically compute approximations to large scale counting or discrete integration problems by using random hashes. The hashes are u…
Robust Gradient Descent via Moment Encoding with LDPC Codes
Raj Kumar Maity, Ankit Singh Rawat, Arya Mazumdar
This paper considers the problem of implementing large-scale gradient descent algorithms in a distributed computing setting in the presence of {\em straggling} processors. To mitig…
On a convergent off -policy temporal difference learning algorithm in on-line learning environment
Prasenjit Karmakar, Rajkumar Maity, Shalabh Bhatnagar
In this paper we provide a rigorous convergence analysis of a "off"-policy temporal difference learning algorithm with linear function approximation and per time-step linear comput…
Shaping Proto-Value Functions via Rewards
Chandrashekar Lakshmi Narayanan, Raj Kumar Maity, Shalabh Bhatnagar
In this paper, we combine task-dependent reward shaping and task-independent proto-value functions to obtain reward dependent proto-value functions (RPVFs). In constructing the RPV…