activity
20182020
most citedSelf-Supervised Learning of Generative Spin-Glasses with Normalizing Flows

6 citations · 13 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG2020

Deep Generative Modeling in Network Science with Applications to Public Policy Research

Gavin S. Hartnett, Raffaele Vardavas, Lawrence Baker +5

Network data is increasingly being used in quantitative, data-driven public policy research. These are typically very rich datasets that contain complex correlations and inter-depe…

cond-mat.dis-nn20204 cited

A Probability Density Theory for Spin-Glass Systems

Gavin S. Hartnett, Masoud Mohseni

Spin-glass systems are universal models for representing many-body phenomena in statistical physics and computer science. High quality solutions of NP-hard combinatorial optimizati…

cs.LG20206 cited

Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows

Gavin S. Hartnett, Masoud Mohseni

Spin-glasses are universal models that can capture complex behavior of many-body systems at the interface of statistical physics and computer science including discrete optimizatio…

hep-th2019

Covariant Noether charges for type IIB and 11-dimensional supergravities

Óscar J. C. Dias, Gavin S. Hartnett, Jorge E. Santos

The covariant Noether charge formalism (also known as the covariant phase method) of Wald and collaborators, including its cohomological extension, is a manifestly covariant Hamilt…

stat.ML20193 cited

Adversarial Examples for Cost-Sensitive Classifiers

Gavin S. Hartnett, Andrew J. Lohn, Alexander P. Sedlack

Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant…

hep-th2018

Holographic dual of hot Polchinski-Strassler quark-gluon plasma

Iosif Bena, Oscar J. C. Dias, Gavin S. Hartnett +2

We construct the supergravity dual of the hot quark-gluon plasma in the mass-deformed Super-Yang-Mills theory (also known as ). The full ten-dimensional…