Gregory Dexter

According to our database, Gregory Dexter authored at least 13 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Stochastic Rounding Implicitly Regularizes Tall-and-Thin Matrices.

Gregory Dexter, Christos Boutsikas, Linkai Ma, Ilse C. F. Ipsen, Petros Drineas

CoRR, 2024

A Precise Characterization of SGD Stability Using Loss Surface Geometry.

Gregory Dexter, Borja Ocejo, S. Sathiya Keerthi, Aman Gupta, Ayan Acharya, Rajiv Khanna

CoRR, 2024

Universal Matrix Sparsifiers and Fast Deterministic Algorithms for Linear Algebra.

Rajarshi Bhattacharjee, Gregory Dexter, Cameron Musco, Archan Ray, Sushant Sachdeva, David P. Woodruff

Proceedings of the 15th Innovations in Theoretical Computer Science Conference, 2024

2023

Feature Space Sketching for Logistic Regression.

Gregory Dexter, Rajiv Khanna, Jawad Raheel, Petros Drineas

CoRR, 2023

Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming.

Gregory Dexter, Petros Drineas, David P. Woodruff, Taisuke Yasuda

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sublinear Time Eigenvalue Approximation via Random Sampling.

Rajarshi Bhattacharjee, Gregory Dexter, Petros Drineas, Cameron Musco, Archan Ray

Proceedings of the 50th International Colloquium on Automata, Languages, and Programming, 2023

2022

Faster Randomized Interior Point Methods for Tall/Wide Linear Programs.

Agniva Chowdhury, Gregory Dexter, Palma London, Haim Avron, Petros Drineas

J. Mach. Learn. Res., 2022

On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming.

Gregory Dexter, Agniva Chowdhury, Haim Avron, Petros Drineas

Proceedings of the International Conference on Machine Learning, 2022

2021

Inverse Reinforcement Learning in the Continuous Setting with Formal Guarantees.

Gregory Dexter, Kevin Bello, Jean Honorio

CoRR, 2021

Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees.

Gregory Dexter, Kevin Bello, Jean Honorio

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Randomized Linear Algebra Approaches to Estimate the von Neumann Entropy of Density Matrices.

Eugenia-Maria Kontopoulou, Gregory-Paul Dexter, Wojciech Szpankowski, Ananth Grama, Petros Drineas

IEEE Trans. Inf. Theory, 2020

2019

An Adversorial Approach to Enable Re-Use of Machine Learning Models and Collaborative Research Efforts Using Synthetic Unstructured Free-Text Medical Data.

Suranga Nath Kasthurirathne, Gregory Dexter, Shaun J. Grannis

Proceedings of the MEDINFO 2019: Health and Wellbeing e-Networks for All, 2019

Comparison of Free-Text Synthetic Data Produced by Three Generative Adversarial Networks for Collaborative Health Data Analytics.

Gregory-Paul Dexter, Shaun J. Grannis, Suranga Nath Kasthurirathne

Proceedings of the AMIA 2019, 2019