Gintare Karolina Dziugaite
Gintare Karolina Dziugaite
Research Scientist, Element AI
Zweryfikowany adres z elementai.com - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Training generative neural networks via maximum mean discrepancy optimization
GK Dziugaite, DM Roy, Z Ghahramani
arXiv preprint arXiv:1505.03906, 2015
3532015
Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data
GK Dziugaite, DM Roy
arXiv preprint arXiv:1703.11008, 2017
2952017
A study of the effect of jpg compression on adversarial images
GK Dziugaite, Z Ghahramani, DM Roy
arXiv preprint arXiv:1608.00853, 2016
2002016
Neural network matrix factorization
GK Dziugaite, DM Roy
arXiv preprint arXiv:1511.06443, 2015
103*2015
Data-dependent PAC-Bayes priors via differential privacy
GK Dziugaite, DM Roy
arXiv preprint arXiv:1802.09583, 2018
542018
The lottery ticket hypothesis at scale
J Frankle, GK Dziugaite, DM Roy, M Carbin
arXiv preprint arXiv:1903.01611 8, 2019
48*2019
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy
GK Dziugaite, DM Roy
34*2018
Linear mode connectivity and the lottery ticket hypothesis
J Frankle, GK Dziugaite, D Roy, M Carbin
International Conference on Machine Learning, 3259-3269, 2020
322020
Roy, and Michael Carbin. The lottery ticket hypothesis at scale
J Frankle, GK Dziugaite, M Daniel
arXiv preprint arXiv:1903.01611 2 (3), 2019
322019
Information-theoretic generalization bounds for sgld via data-dependent estimates
J Negrea, M Haghifam, GK Dziugaite, A Khisti, DM Roy
arXiv preprint arXiv:1911.02151, 2019
292019
Requiem for the max rule?
WJ Ma, S Shen, G Dziugaite, R van den Berg
Vision Research 116, 179-193, 2015
272015
Stabilizing the lottery ticket hypothesis
J Frankle, GK Dziugaite, DM Roy, M Carbin
arXiv preprint arXiv:1903.01611, 2019
212019
Sharpened generalization bounds based on conditional mutual information and an application to noisy, iterative algorithms
M Haghifam, J Negrea, A Khisti, DM Roy, GK Dziugaite
arXiv preprint arXiv:2004.12983, 2020
112020
On the role of data in PAC-Bayes bounds
GK Dziugaite, K Hsu, W Gharbieh, DM Roy
arXiv preprint arXiv:2006.10929, 2020
92020
Relatif: Identifying explanatory training samples via relative influence
E Barshan, ME Brunet, GK Dziugaite
International Conference on Artificial Intelligence and Statistics, 1899-1909, 2020
72020
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
S Fort, GK Dziugaite, M Paul, S Kharaghani, DM Roy, S Ganguli
arXiv preprint arXiv:2010.15110, 2020
62020
In search of robust measures of generalization
GK Dziugaite, A Drouin, B Neal, N Rajkumar, E Caballero, L Wang, ...
arXiv preprint arXiv:2010.11924, 2020
62020
Revisiting generalization for deep learning: PAC-Bayes, flat minima, and generative models
GK Dziugaite
University of Cambridge, 2020
62020
Pruning Neural Networks at Initialization: Why are We Missing the Mark?
J Frankle, GK Dziugaite, DM Roy, M Carbin
arXiv preprint arXiv:2009.08576, 2020
52020
In defense of uniform convergence: Generalization via derandomization with an application to interpolating predictors
J Negrea, GK Dziugaite, D Roy
International Conference on Machine Learning, 7263-7272, 2020
32020
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20