Roi Livni

Gintare Karolina Dziugaite

CoRR, 2024

Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes.

[BibT_eX]

[DOI]

CoRR, 2024

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization.

[BibT_eX]

[DOI]

Idan Attias

Mahdi Haghifam

Daniel M. Roy

CoRR, 2024

Making Progress Based on False Discoveries.

[BibT_eX]

[DOI]

Gintare Karolina Dziugaite

Proceedings of the 15th Innovations in Theoretical Computer Science Conference, 2024

Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing.

[BibT_eX]

[DOI]

Idan Attias

Mahdi Haghifam

Daniel M. Roy

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Can Copyright Be Reduced to Privacy?

[BibT_eX]

[DOI]

Proceedings of the 5th Symposium on Foundations of Responsible Computing, 2024

The sample complexity of ERMs in stochastic convex optimization.

[BibT_eX]

[DOI]

Daniel Carmon

Amir Yehudayoff

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Private and Online Learnability Are Equivalent.

[BibT_eX]

[DOI]

J. ACM, 2022

Benign Underfitting of Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Thinking Outside the Ball: Optimal Learning with Gradient Descent for Generalized Linear Stochastic Convex Optimization.

[BibT_eX]

[DOI]

Idan Amir

Nati Srebro

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Better Best of Both Worlds Bounds for Bandits with Switching Costs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Littlestone Classes are Privately Online Learnable.

[BibT_eX]

[DOI]

Noah Golowich

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Never Go Full Batch (in Stochastic Convex Optimization).

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games.

[BibT_eX]

[DOI]

Steve Hanneke

Proceedings of the Conference on Learning Theory, 2021

SGD Generalizes Better Than GD (And Regularization Doesn't Help).

[BibT_eX]

[DOI]

Idan Amir

Proceedings of the Conference on Learning Theory, 2021

2020

A Limitation of the PAC-Bayes Framework.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Synthetic Data Generators - Sequential and Private.

[BibT_eX]

[DOI]

Olivier Bousquet

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Prediction with Corrupted Expert Advice.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

An Equivalence Between Private Classification and Online Prediction.

[BibT_eX]

[DOI]

Mark Bun

Proceedings of the 61st IEEE Annual Symposium on Foundations of Computer Science, 2020

On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes.

[BibT_eX]

[DOI]

Pravesh K. Kothari

Proceedings of the Algorithmic Learning Theory, 2020

2019

Passing Tests without Memorizing: Two Models for Fooling Discriminators.

[BibT_eX]

[DOI]

Olivier Bousquet

CoRR, 2019

Private PAC learning implies finite Littlestone dimension.

[BibT_eX]

[DOI]

Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, 2019

Graph-based Discriminators: Sample Complexity and Expressiveness.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Generalize Across Tasks: Efficient Algorithms for Linear Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Learning Theory, 2019

2018

Improper Learning by Refuting.

[BibT_eX]

[DOI]

Pravesh K. Kothari

Proceedings of the 9th Innovations in Theoretical Computer Science Conference, 2018

Open problem: Improper learning of mixtures of Gaussians.

[BibT_eX]

[DOI]

Elad Hazan

Proceedings of the Conference On Learning Theory, 2018

2017

On Communication Complexity of Classification Problems.

[BibT_eX]

[DOI]

Electron. Colloquium Comput. Complex., 2017

Learning by Refuting.

[BibT_eX]

[DOI]

Pravesh K. Kothari

CoRR, 2017

Multi-Armed Bandits with Metric Movement Costs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Affine-Invariant Online Optimization and the Low-rank Experts Problem.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Learning Infinite Layer Networks Without the Kernel Trick.

[BibT_eX]

[DOI]

Daniel Carmon

Proceedings of the 34th International Conference on Machine Learning, 2017

Bandits with Movement Costs and Adaptive Pricing.

[BibT_eX]

[DOI]

Proceedings of the 30th Conference on Learning Theory, 2017

Effective Semisupervised Learning on Manifolds.

[BibT_eX]

[DOI]

Shai Shalev-Shwartz

Proceedings of the 30th Conference on Learning Theory, 2017

2016

Representation learning theory (שער נוסף בעברית: תורת למידת הייצוג‏).

[BibT_eX]

[DOI]

PhD thesis, 2016

Learning Infinite-Layer Networks: Beyond the Kernel Trick.

[BibT_eX]

[DOI]

CoRR, 2016

Online Pricing with Strategic and Patient Buyers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Online Learning with Low Rank Experts.

[BibT_eX]

[DOI]

Proceedings of the 29th Conference on Learning Theory, 2016

Improper Deep Kernels.

[BibT_eX]

[DOI]

Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015

Classification with Low Rank and Missing Data.

[BibT_eX]

[DOI]

Elad Hazan

Proceedings of the 32nd International Conference on Machine Learning, 2015

2014

On the Computational Efficiency of Training Neural Networks.

[BibT_eX]

[DOI]

Shai Shalev-Shwartz

Ohad Shamir

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

2013

A Provably Efficient Algorithm for Training Deep Networks

[BibT_eX]

[DOI]

Shai Shalev-Shwartz

Ohad Shamir

CoRR, 2013

Vanishing Component Analysis.

[BibT_eX]

[DOI]

Proceedings of the 30th International Conference on Machine Learning, 2013

Honest Compressions and Their Application to Compression Schemes.

[BibT_eX]

[DOI]

Pierre Simon

Proceedings of the COLT 2013, 2013

2012

A Simple Geometric Interpretation of SVM using Stochastic Adversaries.

[BibT_eX]

[DOI]

Koby Crammer