27 citations · 50 across the 13 of their papers we have counts for
15 papers
Binary Optimization with Complex Constraints via Quantum Approximate Multi-Objective Optimization
Andres Ruiz, Soumyadip Ghosh, Stefan Woerner
We show that a class of binary optimization problems with complex non-quadratic objectives or constraints can be reformulated as multi-objective quadratic unconstrained binary opti…
On Representations of Mean-Field Variational Inference
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki +1
The mean field variational inference (MFVI) formulation restricts the general Bayesian inference problem to the subspace of product measures. We present a framework to analyze MFVI…
A Class of Geometric Structures in Transfer Learning: Minimax Bounds and Optimality
Xuhui Zhang, Jose Blanchet, Soumyadip Ghosh +1
We study the problem of transfer learning, observing that previous efforts to understand its information-theoretic limits do not fully exploit the geometric structure of the source…
Communication-Efficient Algorithms for Solving Pressure Poisson Equation for Multiphase Flows using Parallel Computers
Soumyadip Ghosh, Jiacai Lu, Vijay Gupta +1
Numerical solution of partial differential equations on parallel computers using domain decomposition usually requires synchronization and communication among the processors. These…
Polynomial convergence of iterations of certain random operators in Hilbert space
Soumyadip Ghosh, Yingdong Lu, Tomasz J. Nowicki
We study the convergence of a random iterative sequence of a family of operators on infinite dimensional Hilbert spaces, inspired by the Stochastic Gradient Descent (SGD) algorithm…
Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki
Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are crucially symmetrically distributed. W…
EventGraD: Event-Triggered Communication in Parallel Machine Learning
Soumyadip Ghosh, Bernardo Aquino, Vijay Gupta
Communication in parallel systems imposes significant overhead which often turns out to be a bottleneck in parallel machine learning. To relieve some of this overhead, in this pape…
HMC, an Algorithms in Data Mining, the Functional Analysis approach
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki
The main purpose of this paper is to facilitate the communication between the Analytic, Probabilistic and Algorithmic communities. We present a proof of convergence of the Hamilton…
On Convergence of the Hamiltonian Monte Carlo
Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki
We establish convergence for Hamiltonian Monte Carlo algorithms. More specifically, under mild conditions for the associated Hamiltonian motion, we show that the outputs of t…
Unbiased Gradient Estimation for Distributionally Robust Learning
Soumyadip Ghosh, Mark Squillante
Seeking to improve model generalization, we consider a new approach based on distributionally robust learning (DRL) that applies stochastic gradient descent to the outer minimizati…
Efficient Stochastic Gradient Descent for Learning with Distributionally Robust Optimization
Soumyadip Ghosh, Mark Squillante, Ebisa Wollega
Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formu…
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD
Sanghamitra Dutta, Gauri Joshi, Soumyadip Ghosh +2
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers). Asynchronous methods can allev…
Efficient Estimation in the Tails of Gaussian Copulas
Kalyani Nagaraj, Jie Xu, Raghu Pasupathy +1
We consider the question of efficient estimation in the tails of Gaussian copulas. Our special focus is estimating expectations over multi-dimensional constrained sets that have a…
Robust Analysis in Stochastic Simulation: Computation and Performance Guarantees
Soumyadip Ghosh, Henry Lam
Any performance analysis based on stochastic simulation is subject to the errors inherent in misspecifying the modeling assumptions, particularly the input distributions. In situat…
A strong law for the rate of growth of long latency periods in cloud computing service
Souvik Ghosh, Soumyadip Ghosh
Cloud-computing shares a common pool of resources across customers at a scale that is orders of magnitude larger than traditional multi-user systems. Constituent physical compute s…