no code implementations • 27 Nov 2015 • 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).
no code implementations • 22 May 2018 • Raj Kumar Maity, Ankit Singh Rawat, Arya Mazumdar
We, instead, propose to encode the second-moment of the data with a low density parity-check (LDPC) code.
no code implementations • 29 Jun 2018 • 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.
no code implementations • 18 Nov 2019 • Venkata Gandikota, Daniel Kane, Raj Kumar Maity, Arya Mazumdar
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 communication cost with convergence guarantees in first-order distributed optimization.
no code implementations • 21 Nov 2019 • Avishek Ghosh, Raj Kumar Maity, Swanand Kadhe, Arya Mazumdar, Kannan Ramchandran
Moreover, we analyze the compressed gradient descent algorithm with error feedback (proposed in \cite{errorfeed}) in a distributed setting and in the presence of Byzantine worker machines.
no code implementations • NeurIPS 2020 • 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.
no code implementations • 19 Nov 2020 • Raj Kumar Maity, Cameron Musco
Such matrices generalize Toeplitz and circulant covariance matrices and are widely applied in signal processing applications, where the covariance between two measurements depends on the (shortest path) distance between them in time or space.
no code implementations • 17 Mar 2021 • Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar, Kannan Ramchandran
Moreover, we validate our theoretical findings with experiments using standard datasets and several types of Byzantine attacks, and obtain an improvement of $25\%$ with respect to first order methods in iteration complexity.