Steve Hanneke

CoRR, 2024

Revisiting Agnostic PAC Learning.

[BibT_eX]

[DOI]

Kasper Green Larsen

Nikita Zhivotovskiy

CoRR, 2024

Ramsey Theorems for Trees and a General 'Private Learning Implies Online Learning' Theorem.

[BibT_eX]

[DOI]

CoRR, 2024

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs.

[BibT_eX]

[DOI]

CoRR, 2024

Agnostic Sample Compression Schemes for Regression.

[BibT_eX]

[DOI]

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

Open problem: Direct Sums in Learning Theory.

[BibT_eX]

[DOI]

Tom Waknine

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

List Sample Compression and Uniform Convergence.

[BibT_eX]

[DOI]

Tom Waknine

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

The Star Number and Eluder Dimension: Elementary Observations About the Dimensions of Disagreement.

[BibT_eX]

[DOI]

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Universal Rates for Regression: Separations between Cut-Off and Absolute Loss.

[BibT_eX]

[DOI]

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Dual VC Dimension Obstructs Sample Compression by Embeddings.

[BibT_eX]

[DOI]

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Efficient Agnostic Learning with Average Smoothness.

[BibT_eX]

[DOI]

Guy Kornowski

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

The Dimension of Self-Directed Learning.

[BibT_eX]

[DOI]

Pramith Devulapalli

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

2023

Reliable Learning for Test-time Attacks and Distribution Shift.

[BibT_eX]

[DOI]

CoRR, 2023

Non-stationary Contextual Bandits and Universal Learning.

[BibT_eX]

[DOI]

Moïse Blanchard

Patrick Jaillet

CoRR, 2023

Contextual Bandits and Optimistically Universal Learning.

[BibT_eX]

[DOI]

Moïse Blanchard

Patrick Jaillet

CoRR, 2023

Near-optimal learning with average Hölder smoothness.

[BibT_eX]

[DOI]

Guy Kornowski

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

A Trichotomy for Transductive Online Learning.

[BibT_eX]

[DOI]

Jonathan Shafer

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

Adversarial Resilience in Sequential Prediction via Abstention.

[BibT_eX]

[DOI]

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

Reliable learning in challenging environments.

[BibT_eX]

[DOI]

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

Optimal Learners for Realizable Regression: PAC Learning and Online Learning.

[BibT_eX]

[DOI]

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

Adversarially Robust PAC Learnability of Real-Valued Functions.

[BibT_eX]

[DOI]

Idan Attias

Proceedings of the International Conference on Machine Learning, 2023

Universal Rates for Multiclass Learning.

[BibT_eX]

[DOI]

Qian Zhang

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Multiclass Online Learning and Uniform Convergence.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Limits of Model Selection under Transfer Learning.

[BibT_eX]

[DOI]

Yasaman Mahdaviyeh

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Bandit Learnability can be Undecidable.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Improper Multiclass Boosting.

[BibT_eX]

[DOI]

Nataly Brukhim

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Fine-Grained Distribution-Dependent Learning Curves.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Adversarially Robust Learning of Real-Valued Functions.

[BibT_eX]

[DOI]

Idan Attias

CoRR, 2022

Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization.

[BibT_eX]

[DOI]

Nati Srebro

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

Universal Rates for Interactive Learning.

[BibT_eX]

[DOI]

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

On Optimal Learning Under Targeted Data Poisoning.

[BibT_eX]

[DOI]

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

A Characterization of Semi-Supervised Adversarially Robust PAC Learnability.

[BibT_eX]

[DOI]

Idan Attias

Yishay Mansour

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

Robustly-reliable learners under poisoning attacks.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Universally Consistent Online Learning with Arbitrarily Dependent Responses.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Algorithmic Learning Theory, 29 March, 2022

Universal Online Learning with Unbounded Losses: Memory Is All You Need.

[BibT_eX]

[DOI]

Moïse Blanchard

Romain Cosson

Proceedings of the International Conference on Algorithmic Learning Theory, 29 March, 2022

Transductive Robust Learning Guarantees.

[BibT_eX]

[DOI]

Nathan Srebro

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

A theory of universal learning.

[BibT_eX]

[DOI]

Proceedings of the STOC '21: 53rd Annual ACM SIGACT Symposium on Theory of Computing, 2021

A Theory of PAC Learnability of Partial Concept Classes.

[BibT_eX]

[DOI]

Proceedings of the 62nd IEEE Annual Symposium on Foundations of Computer Science, 2021

Adversarially Robust Learning with Unknown Perturbation Sets.

[BibT_eX]

[DOI]

Nathan Srebro

Proceedings of the Conference on Learning Theory, 2021

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

[BibT_eX]

[DOI]

Roi Livni

Proceedings of the Conference on Learning Theory, 2021

Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible?

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

Robust learning under clean-label attack.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound.

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Learning Theory, 2021

Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Special issue on ALT 2017: Guest Editors' Introduction.

[BibT_eX]

[DOI]

Lev Reyzin

Theor. Comput. Sci., 2020

A No-Free-Lunch Theorem for MultiTask Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Reducing Adversarially Robust Learning to Non-Robust PAC Learning.

[BibT_eX]

[DOI]

Nati Srebro

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

Universal Bayes Consistency in Metric Spaces.

[BibT_eX]

[DOI]

Proceedings of the Information Theory and Applications Workshop, 2020

Proper Learning, Helly Number, and an Optimal SVM Bound.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2020

2019

Optimality of SVM: Novel proofs and tighter bounds.

[BibT_eX]

[DOI]

Theor. Comput. Sci., 2019

On the Value of Target Data in Transfer Learning.

[BibT_eX]

[DOI]

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

VC Classes are Adversarially Robustly Learnable, but Only Improperly.

[BibT_eX]

[DOI]

Nathan Srebro

Proceedings of the Conference on Learning Theory, 2019

Sample Compression for Real-Valued Learners.

[BibT_eX]

[DOI]

Menachem Sadigurschi

Proceedings of the Algorithmic Learning Theory, 2019

A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes.

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Learning Theory, 2019

Statistical Learning under Nonstationary Mixing Processes.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

Localization of VC classes: Beyond local Rademacher complexities.

[BibT_eX]

[DOI]

Nikita Zhivotovskiy

Theor. Comput. Sci., 2018

Bounds on the minimax rate for estimating a prior over a VC class from independent learning tasks.

[BibT_eX]

[DOI]

Theor. Comput. Sci., 2018

Testing piecewise functions.

[BibT_eX]

[DOI]

Theor. Comput. Sci., 2018

Agnostic Sample Compression for Linear Regression.

[BibT_eX]

[DOI]

Menachem Sadigurschi

CoRR, 2018

A New Lower Bound for Agnostic Learning with Sample Compression Schemes.

[BibT_eX]

[DOI]

CoRR, 2018

Actively Avoiding Nonsense in Generative Models.

[BibT_eX]

[DOI]

Proceedings of the Conference On Learning Theory, 2018

2017

Learning with Changing Features.

[BibT_eX]

[DOI]

Amit Dhurandhar

CoRR, 2017

2016

Refined Error Bounds for Several Learning Algorithms.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2016

The Optimal Sample Complexity of PAC Learning.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2016

2015

A compression technique for analyzing disagreement-based active learning.

[BibT_eX]

[DOI]

Yair Wiener

Ran El-Yaniv

J. Mach. Learn. Res., 2015

Minimax analysis of active learning.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2015

Statistical Learning under Nonstationary Mixing Processes.

[BibT_eX]

[DOI]

Tommi S. Jaakkola

CoRR, 2015

Learning with a Drifting Target Concept.

[BibT_eX]

[DOI]

Varun Kanade

Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

2014

Theory of Disagreement-Based Active Learning.

[BibT_eX]

[DOI]

Found. Trends Mach. Learn., 2014

2013

A theory of transfer learning with applications to active learning.

[BibT_eX]

[DOI]

Mach. Learn., 2013

Activized Learning with Uniform Classification Noise.

[BibT_eX]

[DOI]

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

2012

Activized Learning: Transforming Passive to Active with Improved Label Complexity.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2012

Robust Interactive Learning.

[BibT_eX]

[DOI]

Maria-Florina Balcan

Proceedings of the COLT 2012, 2012

Surrogate Losses in Passive and Active Learning

[BibT_eX]

[DOI]

CoRR, 2012

2011

Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning.

[BibT_eX]

[DOI]

Proceedings of the COLT 2011, 2011

The Sample Complexity of Self-Verifying Bayesian Active Learning.

[BibT_eX]

[DOI]

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

2010

The true sample complexity of active learning.

[BibT_eX]

[DOI]

Maria-Florina Balcan

Jennifer Wortman Vaughan

Mach. Learn., 2010

Negative Results for Active Learning with Convex Losses.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Bayesian Active Learning Using Arbitrary Binary Valued Queries.

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Learning Theory, 21st International Conference, 2010

2009

Network Completion and Survey Sampling.

[BibT_eX]

[DOI]

Eric P. Xing

Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, 2009

Adaptive Rates of Convergence in Active Learning.

[BibT_eX]

[DOI]

Proceedings of the COLT 2009, 2009

2007

A bound on the label complexity of agnostic active learning.

[BibT_eX]

[DOI]

Proceedings of the Machine Learning, 2007

Recovering temporally rewiring networks: a model-based approach.

[BibT_eX]

[DOI]

Proceedings of the Machine Learning, 2007

Teaching Dimension and the Complexity of Active Learning.

[BibT_eX]

[DOI]

Proceedings of the Learning Theory, 20th Annual Conference on Learning Theory, 2007

2006

Discrete Temporal Models of Social Networks.

[BibT_eX]

[DOI]

Eric P. Xing

Proceedings of the Statistical Network Analysis: Models, Issues, and New Directions, 2006

An analysis of graph cut size for transductive learning.

[BibT_eX]

[DOI]