Accueil
Équipe
Publications
Open Source
Démos
Évènements
Blog
Carrières
Nous joindre
Français
Français
English
ServiceNow
ServiceNow recherche
Tags
Trustworthiness
ServiceNow recherche
Trustworthiness
Linear Mode Connectivity and the Lottery Ticket Hypothesis
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random …
Jonathan Frankle
,
Gintare Karolina Dziugaite
,
Daniel M. Roy
,
Michael Carbin
International Conference on Machine Learning (ICML), 2020.
PDF
Citation
RelatIF: Identifying Explanatory Training Examples via Relative Influence
In this work, we focus on the use of influence functions to identify relevant training examples that one might hope …
Elnaz Barshan
,
Marc-Etienne Brunet
,
Gintare Karolina Dziugaite
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
PDF
Citation
Stochastic Neural Network with Kronecker Flow
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their …
Chin-Wei Huang
,
Ahmed Touati
,
Pascal Vincent
,
Gintare Karolina Dziugaite
,
Alexandre Lacoste
,
Aaron Courville
International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
PDF
Citation
Stabilizing the Lottery Ticket Hypothesis
Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the …
Jonathan Frankle
,
Gintare Karolina Dziugaite
,
Daniel M. Roy
,
Michael Carbin
Association for the Advancement of Artificial Intelligence (AAAI), 2020.
PDF
Citation
Linear Mode Connectivity and the Lottery Ticket Hypothesis
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random …
Jonathan Frankle
,
Gintare Karolina Dziugaite
,
Daniel M. Roy
,
Michael Carbin
Women in Machine Learning (WiML), 2019.
PDF
Citation
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and …
Jeffrey Negrea
,
Mahdi Haghifam
,
Gintare Karolina Dziugaite
,
Ashish Khisti
,
Daniel M. Roy
Conference on Neural Information Processing Systems (NeurIPS), 2019.
PDF
Citation
Objects of violence: synthetic data for practical ML in human rights investigations
We introduce a machine learning workflow to search for, identify, and meaningfully triage videos and images of munitions, weapons, and …
Lachlan Kermode
,
Jan Freyberg
,
Alican Akturk
,
Robert Trafford
,
Denis Kocetkov
,
Rafael Pardinas
,
Eyal Weizman
,
Julien Cornebise
Workshop at the Neural Information Processing Systems (NeurIPS), 2019.
PDF
Citation
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Recent works have shown that stochastic gradient descent (SGD) achieves the fast convergence rates of full-batch gradient descent for …
Sharan Vaswani
,
Aaron Mishkin
,
Issam H. Laradji
,
Mark Schmidt
,
Gauthier Gidel
,
Simon Lacoste-Julien
Conference on Neural Information Processing Systems (NeurIPS), 2019.
PDF
Citation
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and …
Jeffrey Negrea
,
Mahdi Haghifam
,
Gintare Karolina Dziugaite
,
Ashish Khisti
,
Daniel M. Roy
Workshop at the International Conference on Machine Learning (ICML), 2019.
PDF
Citation
Stochastic Neural Network with Kronecker Flow
Recent advances in variational inference enable the modelling of highly structured joint distributions, but are limited in their …
Chin-Wei Huang
,
Ahmed Touati
,
Pascal Vincent
,
Gintare Karolina Dziugaite
,
Alexandre Lacoste
,
Aaron Courville
Workshop at the International Conference on Machine Learning (ICML), 2019.
PDF
Citation
«
»
Citation
×