default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDGintare Karolina Dziugaite
Karolina Dziugaite
Person information
- affiliation: Google Research
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j1]Nikita Dhawan, Nicole Mitchell, Zachary Charles, Zachary Garrett, Gintare Karolina Dziugaite:
Leveraging Function Space Aggregation for Federated Learning at Scale. Trans. Mach. Learn. Res. 2024 (2024)- [c28]Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman:
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias. AISTATS 2024: 2953-2961 - [c27]Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite:
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning. ICLR 2024 - [c26]Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy:
Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing. ICML 2024 - [c25]Johan Samir Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob Nicolaus Foerster, Gintare Karolina Dziugaite, Doina Precup, Pablo Samuel Castro:
Mixtures of Experts Unlock Parameter Scaling for Deep RL. ICML 2024 - [c24]Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite:
Simultaneous Linear Connectivity of Neural Networks Modulo Permutation. ECML/PKDD (7) 2024: 262-279 - [i42]Devin Kwok, Nikhil Anand, Jonathan Frankle, Gintare Karolina Dziugaite, David Rolnick:
Dataset Difficulty and the Role of Inductive Bias. CoRR abs/2401.01867 (2024) - [i41]Johan S. Obando-Ceron, Ghada Sokar, Timon Willi, Clare Lyle, Jesse Farebrother, Jakob N. Foerster, Gintare Karolina Dziugaite, Doina Precup, Pablo Samuel Castro:
Mixtures of Experts Unlock Parameter Scaling for Deep RL. CoRR abs/2402.08609 (2024) - [i40]Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam, Roi Livni, Daniel M. Roy:
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization. CoRR abs/2402.09327 (2024) - [i39]Tejas Kasetty, Divyat Mahajan, Gintare Karolina Dziugaite, Alexandre Drouin, Dhanya Sridhar:
Evaluating Interventional Reasoning Capabilities of Large Language Models. CoRR abs/2404.05545 (2024) - [i38]Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick, Gintare Karolina Dziugaite:
Simultaneous linear connectivity of neural networks modulo permutation. CoRR abs/2404.06498 (2024) - [i37]Riyasat Ohib, Bishal Thapaliya, Gintare Karolina Dziugaite, Jingyu Liu, Vince D. Calhoun, Sergey M. Plis:
Unmasking Efficiency: Learning Salient Sparse Models in Non-IID Federated Learning. CoRR abs/2405.09037 (2024) - [i36]Nazanin Mohammadi Sepahvand, Vincent Dumoulin, Eleni Triantafillou, Gintare Karolina Dziugaite:
Data Selection for Transfer Unlearning. CoRR abs/2405.10425 (2024) - [i35]Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa, Jamie Hayes, Meghdad Kurmanji, Kairan Zhao, Vincent Dumoulin, Júlio C. S. Jacques Júnior, Ioannis Mitliagkas, Jun Wan, Lisheng Sun-Hosoya, Sergio Escalera, Gintare Karolina Dziugaite, Peter Triantafillou, Isabelle Guyon:
Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition. CoRR abs/2406.09073 (2024) - [i34]Timon Willi, Johan S. Obando-Ceron, Jakob N. Foerster, Karolina Dziugaite, Pablo Samuel Castro:
Mixture of Experts in a Mixture of RL settings. CoRR abs/2406.18420 (2024) - 2023
- [c23]Mahdi Haghifam, Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite:
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. ALT 2023: 663-706 - [c22]Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite:
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? ICLR 2023 - [c21]Marco Fumero, Emanuele Rodolà, Clémentine Dominé, Francesco Locatello, Karolina Dziugaite, Mathilde Caron:
Preface of UniReps: the First Workshop on Unifying Representations in Neural Models. UniReps 2023: 1-10 - [e1]Marco Fumero, Emanuele Rodolà, Clémentine Dominé, Francesco Locatello, Karolina Dziugaite, Mathilde Caron:
Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models, 15 December 2023, Ernest N. Morial Convention Center, New Orleans, USA. Proceedings of Machine Learning Research 243, PMLR 2023 [contents] - [i33]Joo Hyung Lee, Wonpyo Park, Nicole Mitchell, Jonathan Pilault, Johan S. Obando-Ceron, Han-Byul Kim, Namhoon Lee, Elias Frantar, Yun Long, Amir Yazdanbakhsh, Shivani Agrawal, Suvinay Subramanian, Xin Wang, Sheng-Chun Kao, Xingyao Zhang, Trevor Gale, Aart Bik, Woohyun Han, Milen Ferev, Zhonglin Han, Hong-Seok Kim, Yann N. Dauphin, Karolina Dziugaite, Pablo Samuel Castro, Utku Evci:
JaxPruner: A concise library for sparsity research. CoRR abs/2304.14082 (2023) - [i32]Yu Yang, Eric Gan, Gintare Karolina Dziugaite, Baharan Mirzasoleiman:
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias. CoRR abs/2305.18761 (2023) - [i31]Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite:
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning. CoRR abs/2310.04680 (2023) - [i30]Nikita Dhawan, Nicole Mitchell, Zachary Charles, Zachary Garrett, Gintare Karolina Dziugaite:
Leveraging Function Space Aggregation for Federated Learning at Scale. CoRR abs/2311.10291 (2023) - 2022
- [c20]Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugaite:
Understanding Generalization via Leave-One-Out Conditional Mutual Information. ISIT 2022: 2487-2492 - [c19]Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, Gintare Karolina Dziugaite:
Pruning's Effect on Generalization Through the Lens of Training and Regularization. NeurIPS 2022 - [c18]Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite:
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. NeurIPS 2022 - [i29]Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite:
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. CoRR abs/2206.01278 (2022) - [i28]Mahdi Haghifam, Shay Moran, Daniel M. Roy, Gintare Karolina Dziugaite:
Understanding Generalization via Leave-One-Out Conditional Mutual Information. CoRR abs/2206.14800 (2022) - [i27]Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite:
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? CoRR abs/2210.03044 (2022) - [i26]Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, Gintare Karolina Dziugaite:
Pruning's Effect on Generalization Through the Lens of Training and Regularization. CoRR abs/2210.13738 (2022) - [i25]Zachary Ankner, Alex Renda, Gintare Karolina Dziugaite, Jonathan Frankle, Tian Jin:
The Effect of Data Dimensionality on Neural Network Prunability. CoRR abs/2212.00291 (2022) - [i24]Mahdi Haghifam, Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite:
Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization. CoRR abs/2212.13556 (2022) - 2021
- [c17]Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Gabriel Arpino, Daniel M. Roy:
On the role of data in PAC-Bayes. AISTATS 2021: 604-612 - [c16]Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin:
Pruning Neural Networks at Initialization: Why Are We Missing the Mark? ICLR 2021 - [c15]Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite:
Deep Learning on a Data Diet: Finding Important Examples Early in Training. NeurIPS 2021: 20596-20607 - [c14]Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy:
Towards a Unified Information-Theoretic Framework for Generalization. NeurIPS 2021: 26370-26381 - [i23]Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite:
Deep Learning on a Data Diet: Finding Important Examples Early in Training. CoRR abs/2107.07075 (2021) - [i22]Soufiane Hayou, Bobby He, Gintare Karolina Dziugaite:
Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning. CoRR abs/2110.11804 (2021) - [i21]Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy:
Towards a Unified Information-Theoretic Framework for Generalization. CoRR abs/2111.05275 (2021) - 2020
- [c13]Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite:
RelatIF: Identifying Explanatory Training Samples via Relative Influence. AISTATS 2020: 1899-1909 - [c12]Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron C. Courville:
Stochastic Neural Network with Kronecker Flow. AISTATS 2020: 4184-4194 - [c11]Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin:
Linear Mode Connectivity and the Lottery Ticket Hypothesis. ICML 2020: 3259-3269 - [c10]Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy:
In Defense of Uniform Convergence: Generalization via Derandomization with an Application to Interpolating Predictors. ICML 2020: 7263-7272 - [c9]Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy:
In search of robust measures of generalization. NeurIPS 2020 - [c8]Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli:
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. NeurIPS 2020 - [c7]Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite:
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms. NeurIPS 2020 - [c6]Yiding Jiang, Parth Natekar, Manik Sharma, Sumukh K. Aithal, Dhruva Kashyap, Natarajan Subramanyam, Carlos Lassance, Daniel M. Roy, Gintare Karolina Dziugaite, Suriya Gunasekar, Isabelle Guyon, Pierre Foret, Scott Yak, Hossein Mobahi, Behnam Neyshabur, Samy Bengio:
Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning. NeurIPS (Competition and Demos) 2020: 170-190 - [i20]Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite:
RelatIF: Identifying Explanatory Training Examples via Relative Influence. CoRR abs/2003.11630 (2020) - [i19]Mahdi Haghifam, Jeffrey Negrea, Ashish Khisti, Daniel M. Roy, Gintare Karolina Dziugaite:
Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms. CoRR abs/2004.12983 (2020) - [i18]Gintare Karolina Dziugaite, Kyle Hsu, Waseem Gharbieh, Daniel M. Roy:
On the role of data in PAC-Bayes bounds. CoRR abs/2006.10929 (2020) - [i17]Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin:
Pruning Neural Networks at Initialization: Why are We Missing the Mark? CoRR abs/2009.08576 (2020) - [i16]Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal, Nitarshan Rajkumar, Ethan Caballero, Linbo Wang, Ioannis Mitliagkas, Daniel M. Roy:
In Search of Robust Measures of Generalization. CoRR abs/2010.11924 (2020) - [i15]Gintare Karolina Dziugaite, Shai Ben-David, Daniel M. Roy:
Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability. CoRR abs/2010.13764 (2020) - [i14]Stanislav Fort, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli:
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel. CoRR abs/2010.15110 (2020) - [i13]Mahdi Haghifam, Gintare Karolina Dziugaite, Shay Moran, Daniel M. Roy:
On the Information Complexity of Proper Learners for VC Classes in the Realizable Case. CoRR abs/2011.02970 (2020) - [i12]Yiding Jiang, Pierre Foret, Scott Yak, Daniel M. Roy, Hossein Mobahi, Gintare Karolina Dziugaite, Samy Bengio, Suriya Gunasekar, Isabelle Guyon, Behnam Neyshabur:
NeurIPS 2020 Competition: Predicting Generalization in Deep Learning. CoRR abs/2012.07976 (2020)
2010 – 2019
- 2019
- [b1]Gintare Karolina Dziugaite:
Revisiting generalization for deep learning: PAC-Bayes, flat minima, and generative models. University of Cambridge, UK, 2019 - [c5]Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy:
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. NeurIPS 2019: 11013-11023 - [i11]Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin:
The Lottery Ticket Hypothesis at Scale. CoRR abs/1903.01611 (2019) - [i10]Chin-Wei Huang, Ahmed Touati, Pascal Vincent, Gintare Karolina Dziugaite, Alexandre Lacoste, Aaron C. Courville:
Stochastic Neural Network with Kronecker Flow. CoRR abs/1906.04282 (2019) - [i9]Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy:
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. CoRR abs/1911.02151 (2019) - [i8]Jeffrey Negrea, Gintare Karolina Dziugaite, Daniel M. Roy:
In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors. CoRR abs/1912.04265 (2019) - [i7]Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin:
Linear Mode Connectivity and the Lottery Ticket Hypothesis. CoRR abs/1912.05671 (2019) - 2018
- [c4]Gintare Karolina Dziugaite, Daniel M. Roy:
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors. ICML 2018: 1376-1385 - [c3]Gintare Karolina Dziugaite, Daniel M. Roy:
Data-dependent PAC-Bayes priors via differential privacy. NeurIPS 2018: 8440-8450 - [i6]Gintare Karolina Dziugaite, Daniel M. Roy:
Data-dependent PAC-Bayes priors via differential privacy. CoRR abs/1802.09583 (2018) - 2017
- [c2]Gintare Karolina Dziugaite, Daniel M. Roy:
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. UAI 2017 - [i5]Gintare Karolina Dziugaite, Daniel M. Roy:
Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data. CoRR abs/1703.11008 (2017) - [i4]Gintare Karolina Dziugaite, Daniel M. Roy:
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy. CoRR abs/1712.09376 (2017) - 2016
- [i3]Gintare Karolina Dziugaite, Zoubin Ghahramani, Daniel M. Roy:
A study of the effect of JPG compression on adversarial images. CoRR abs/1608.00853 (2016) - 2015
- [c1]Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani:
Training generative neural networks via Maximum Mean Discrepancy optimization. UAI 2015: 258-267 - [i2]Gintare Karolina Dziugaite, Daniel M. Roy, Zoubin Ghahramani:
Training generative neural networks via Maximum Mean Discrepancy optimization. CoRR abs/1505.03906 (2015) - [i1]Gintare Karolina Dziugaite, Daniel M. Roy:
Neural Network Matrix Factorization. CoRR abs/1511.06443 (2015)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-02 21:39 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
