Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Gintare Karolina Dziugaite

Gintare Karolina Dziugaite

Element AI

Deep Learning on a Data Diet: Finding Important Examples Early in Training


Jul 15, 2021
Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite

Figure 1 for Deep Learning on a Data Diet: Finding Important Examples Early in Training
Figure 2 for Deep Learning on a Data Diet: Finding Important Examples Early in Training
Figure 3 for Deep Learning on a Data Diet: Finding Important Examples Early in Training
Figure 4 for Deep Learning on a Data Diet: Finding Important Examples Early in Training
* 18 pages, 16 figures 
  Access Paper or Ask Questions

NeurIPS 2020 Competition: Predicting Generalization in Deep Learning


Dec 14, 2020
Yiding Jiang, Pierre Foret, Scott Yak, Daniel M. Roy, Hossein Mobahi, Gintare Karolina Dziugaite, Samy Bengio, Suriya Gunasekar, Isabelle Guyon, Behnam Neyshabur

Figure 1 for NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
* 20 pages, 2 figures. Accepted for NeurIPS 2020 Competitions Track. Lead organizer: Yiding Jiang 
  Access Paper or Ask Questions

On the Information Complexity of Proper Learners for VC Classes in the Realizable Case


Nov 05, 2020
Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy

* 5 Pages 
  Access Paper or Ask Questions

Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel


Oct 28, 2020
Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli

Figure 1 for Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
Figure 2 for Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
Figure 3 for Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
Figure 4 for Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
* 19 pages, 19 figures, In Advances in Neural Information Processing Systems 34 (NeurIPS 2020) 
  Access Paper or Ask Questions

Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability


Oct 28, 2020
Gintare Karolina Dziugaite, Shai Ben-David, Daniel M. Roy

Figure 1 for Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability
* 12 pages; minor edits 
  Access Paper or Ask Questions

In Search of Robust Measures of Generalization


Oct 22, 2020
Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy

Figure 1 for In Search of Robust Measures of Generalization
Figure 2 for In Search of Robust Measures of Generalization
Figure 3 for In Search of Robust Measures of Generalization
Figure 4 for In Search of Robust Measures of Generalization
* 27 pages, 11 figures, 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada 
  Access Paper or Ask Questions

Pruning Neural Networks at Initialization: Why are We Missing the Mark?


Sep 18, 2020
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin

Figure 1 for Pruning Neural Networks at Initialization: Why are We Missing the Mark?
Figure 2 for Pruning Neural Networks at Initialization: Why are We Missing the Mark?
Figure 3 for Pruning Neural Networks at Initialization: Why are We Missing the Mark?
Figure 4 for Pruning Neural Networks at Initialization: Why are We Missing the Mark?

  Access Paper or Ask Questions

On the role of data in PAC-Bayes bounds


Jun 19, 2020
Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Daniel M. Roy

Figure 1 for On the role of data in PAC-Bayes bounds
Figure 2 for On the role of data in PAC-Bayes bounds
Figure 3 for On the role of data in PAC-Bayes bounds
Figure 4 for On the role of data in PAC-Bayes bounds
* 23 pages, 7 figures 
  Access Paper or Ask Questions

Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms


Apr 27, 2020
Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite

Figure 1 for Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
Figure 2 for Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms
* 17 pages 
  Access Paper or Ask Questions

RelatIF: Identifying Explanatory Training Examples via Relative Influence


Mar 25, 2020
Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite

Figure 1 for RelatIF: Identifying Explanatory Training Examples via Relative Influence
Figure 2 for RelatIF: Identifying Explanatory Training Examples via Relative Influence
Figure 3 for RelatIF: Identifying Explanatory Training Examples via Relative Influence
Figure 4 for RelatIF: Identifying Explanatory Training Examples via Relative Influence

  Access Paper or Ask Questions

Linear Mode Connectivity and the Lottery Ticket Hypothesis


Dec 11, 2019
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin

Figure 1 for Linear Mode Connectivity and the Lottery Ticket Hypothesis
Figure 2 for Linear Mode Connectivity and the Lottery Ticket Hypothesis
Figure 3 for Linear Mode Connectivity and the Lottery Ticket Hypothesis
Figure 4 for Linear Mode Connectivity and the Lottery Ticket Hypothesis
* This submission subsumes 1903.01611 ("Stabilizing the Lottery Ticket Hypothesis" and "The Lottery Ticket Hypothesis at Scale") 
  Access Paper or Ask Questions

In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors


Dec 09, 2019
Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy

Figure 1 for In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors
* 12 pages 
  Access Paper or Ask Questions

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates


Nov 08, 2019
Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy

Figure 1 for Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Figure 2 for Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Figure 3 for Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Figure 4 for Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
* 23 pages, 1 figure. To appear in, Advances in Neural Information Processing Systems (33), 2019 
  Access Paper or Ask Questions

Stochastic Neural Network with Kronecker Flow


Jun 10, 2019
Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron Courville

Figure 1 for Stochastic Neural Network with Kronecker Flow
Figure 2 for Stochastic Neural Network with Kronecker Flow
Figure 3 for Stochastic Neural Network with Kronecker Flow
Figure 4 for Stochastic Neural Network with Kronecker Flow
* 18 pages 
  Access Paper or Ask Questions

The Lottery Ticket Hypothesis at Scale


Mar 05, 2019
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin

Figure 1 for The Lottery Ticket Hypothesis at Scale
Figure 2 for The Lottery Ticket Hypothesis at Scale
Figure 3 for The Lottery Ticket Hypothesis at Scale
Figure 4 for The Lottery Ticket Hypothesis at Scale

  Access Paper or Ask Questions

Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors


Mar 03, 2018
Gintare Karolina Dziugaite, Daniel M. Roy

Figure 1 for Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
Figure 2 for Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
Figure 3 for Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
Figure 4 for Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
* 18 pages, 6 figures; differentially private PAC-Bayes theorem moved to arXiv:1802.09583; new empirical results 
  Access Paper or Ask Questions

Data-dependent PAC-Bayes priors via differential privacy


Feb 26, 2018
Gintare Karolina Dziugaite, Daniel M. Roy

Figure 1 for Data-dependent PAC-Bayes priors via differential privacy
Figure 2 for Data-dependent PAC-Bayes priors via differential privacy
* 17 pages, 2 figures; subsumes and extends some results first reported in arXiv:1712.09376 
  Access Paper or Ask Questions

Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data


Oct 19, 2017
Gintare Karolina Dziugaite, Daniel M. Roy

Figure 1 for Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
Figure 2 for Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
* Proceedings of the Thirty-Third Conference on Uncertainty in Artificial Intelligence, UAI 2016, August 11--15, 2017, Sydney, NSW, Australia 
 * 14 pages, 1 table, 2 figures. Corresponds with UAI camera ready and supplement. Includes additional references and related experiments 
  Access Paper or Ask Questions

A study of the effect of JPG compression on adversarial images


Aug 02, 2016
Gintare Karolina Dziugaite, Zoubin Ghahramani, Daniel M. Roy

Figure 1 for A study of the effect of JPG compression on adversarial images
Figure 2 for A study of the effect of JPG compression on adversarial images
Figure 3 for A study of the effect of JPG compression on adversarial images
Figure 4 for A study of the effect of JPG compression on adversarial images
* 8 pages, 4 figures 
  Access Paper or Ask Questions

Neural Network Matrix Factorization


Dec 15, 2015
Gintare Karolina Dziugaite, Daniel M. Roy

Figure 1 for Neural Network Matrix Factorization
Figure 2 for Neural Network Matrix Factorization
* Minor modifications to notation. Added additional experiments and discussion. 7 pages, 2 tables 
  Access Paper or Ask Questions

Training generative neural networks via Maximum Mean Discrepancy optimization


May 14, 2015
Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani

Figure 1 for Training generative neural networks via Maximum Mean Discrepancy optimization
Figure 2 for Training generative neural networks via Maximum Mean Discrepancy optimization
Figure 3 for Training generative neural networks via Maximum Mean Discrepancy optimization
* 10 pages, to appear in Uncertainty in Artificial Intelligence (UAI) 2015 
  Access Paper or Ask Questions