activity
20172022
most citedQuantum Topological Data Analysis with Linear Depth and Exponential Speedup

15 citations · 27 across the 8 of their papers we have counts for

collaborators

13 papers

cs.LG20222 cited

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…

quant-ph202115 cited

Quantum Topological Data Analysis with Linear Depth and Exponential Speedup

Shashanka Ubaru, Ismail Yunus Akhalwaya, Mark S. Squillante +2

Quantum computing offers the potential of exponential speedups for certain classical computations. Over the last decade, many quantum machine learning (QML) algorithms have been pr…

cs.ET2021

Solving sparse linear systems with approximate inverse preconditioners on analog devices

Vasileios Kalantzis, Anshul Gupta, Lior Horesh +3

Sparse linear system solvers are computationally expensive kernels that lie at the heart of numerous applications. This paper proposes a flexible preconditioning framework to subst…

stat.ML20201 cited

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…

math.OC2019

Optimal Scheduling Control in Fluid Models of General Input-Queued Switches

Yingdong Lu, Mark S. Squillante, Tonghoon Suk

Most of the early input-queued switch research focused on establishing throughput optimality of the max-weight scheduling policy, with some recent research showing that max-weight…

math.OC2019

On Heavy-Traffic Optimal Scaling of -Weighted MaxWeight Scheduling in Input-Queued Switches

Yingdong Lu, Siva Theja Maguluri, Mark S. Squillante +1

We consider the optimal control of input-queued switches under a cost-weighted variant of MaxWeight scheduling, for which we establish theoretical properties that include showing t…