Accueil
Équipe
Publications
Open Source
Démos
Évènements
Blog
Carrières
Nous joindre
Français
Français
English
ServiceNow
ServiceNow recherche
Tags
Guarantees
ServiceNow recherche
Guarantees
Egocentric Planning for Scalable Embodied Task Achievement
Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing …
Xiaotian Liu
,
Hector Palacios
,
Christian Muise
Conference on Neural Information Processing Systems (NeurIPS), 2023.
PDF
Citation
On the role of data in PAC-Bayes bounds
The dominant term in PAC-Bayes bounds is often the Kullback–Leibler divergence between the posterior and prior. For so-called …
Gintare Karolina Dziugaite
,
Kyle Hsu
,
Waseem Gharbieh
,
Gabriel Arpino
,
Daniel M. Roy
International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
PDF
Citation
Code
An empirical study of loss landscape geometry and evolution of the data-dependent Neural Tangent Kernel
In suitably initialized wide networks, small learning rates transform deep neural networks (DNNs) into neural tangent kernel (NTK) …
Stanislav Fort
,
Gintare Karolina Dziugaite
,
Mansheej Paul
,
Sepideh Kharaghani
,
Daniel M. Roy
,
Surya Ganguli
Conference on Neural Information Processing Systems (NeurIPS), 2020.
PDF
Citation
Vidéo
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy-Gradient Iterative Algorithms
The information-theoretic framework of Russo and J. Zou (2016) and Xu and Raginsky (2017) provides bounds on the generalization error …
Mahdi Haghifam
,
Jeffrey Negrea
,
Ashish Khisti
,
Daniel M. Roy
,
Gintare Karolina Dziugaite
Conference on Neural Information Processing Systems (NeurIPS), 2020.
PDF
Citation
On the Information Complexity of Proper Learners for VC Classes in the Realizable Case
We provide a negative resolution to a conjecture of Steinke and Zakynthinou (2020a), by showing that their bound on the conditional …
Mahdi Haghifam
,
Gintare Karolina Dziugaite
,
Shay Moran
,
Daniel M. Roy
ArXiv, 2020.
PDF
Citation
In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors
We propose to study the generalization error of a learned predictor ĥ in terms of that of a surrogate (potentially randomized) …
Jeffrey Negrea
,
Gintare Karolina Dziugaite
,
Daniel M. Roy
International Conference on Machine Learning (ICML), 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
International Conference on Machine Learning (ICML), 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
»
Citation
×