4 citations · 7 across the 6 of their papers we have counts for
8 papers
Stochastic Rounding Implicitly Regularizes Tall-and-Thin Matrices
Gregory Dexter, Christos Boutsikas, Linkai Ma +2
Motivated by the popularity of stochastic rounding in the context of machine learning and the training of large-scale deep neural network models, we consider stochastic nearness ro…
Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming
Gregory Dexter, Petros Drineas, David P. Woodruff +1
Sketching algorithms have recently proven to be a powerful approach both for designing low-space streaming algorithms as well as fast polynomial time approximation schemes (PTAS).…
Universal Matrix Sparsifiers and Fast Deterministic Algorithms for Linear Algebra
Rajarshi Bhattacharjee, Gregory Dexter, Cameron Musco +3
Let satisfy , where is the all ones matrix and is the spectral norm. It is well-kno…
Feature Space Sketching for Logistic Regression
Gregory Dexter, Rajiv Khanna, Jawad Raheel +1
We present novel bounds for coreset construction, feature selection, and dimensionality reduction for logistic regression. All three approaches can be thought of as sketching the l…
Faster Randomized Interior Point Methods for Tall/Wide Linear Programs
Agniva Chowdhury, Gregory Dexter, Palma London +2
Linear programming (LP) is an extremely useful tool which has been successfully applied to solve various problems in a wide range of areas, including operations research, engineeri…
On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming
Gregory Dexter, Agniva Chowdhury, Haim Avron +1
Interior point methods (IPMs) are a common approach for solving linear programs (LPs) with strong theoretical guarantees and solid empirical performance. The time complexity of the…
Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees
Gregory Dexter, Kevin Bello, Jean Honorio
Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior. The IRL setting is remarkably useful for automated…
Randomized Linear Algebra Approaches to Estimate the Von Neumann Entropy of Density Matrices
Eugenia-Maria Kontopoulou, Gregory-Paul Dexter, Wojciech Szpankowski +2
Thevon Neumann entropy, named after John von Neumann, is an extension of the classical concept of entropy to the field of quantum mechanics. From a numerical perspective, von Neuma…