b'Steve Hanneke'

research

∙ 07/07/2023

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

In this work, we aim to characterize the statistical complexity of reali...

0 Idan Attias, et al. ∙

research

∙ 07/05/2023

Universal Rates for Multiclass Learning

We study universal rates for multiclass classification, establishing the...

0 Steve Hanneke, et al. ∙

research

∙ 06/22/2023

Adversarial Resilience in Sequential Prediction via Abstention

We study the problem of sequential prediction in the stochastic setting ...

0 Surbhi Goel, et al. ∙

research

∙ 04/29/2023

Limits of Model Selection under Transfer Learning

Theoretical studies on transfer learning or domain adaptation have so fa...

0 Steve Hanneke, et al. ∙

research

∙ 04/06/2023

Reliable Learning for Test-time Attacks and Distribution Shift

Machine learning algorithms are often used in environments which are not...

0 Maria-Florina Balcan, et al. ∙

research

∙ 02/27/2023

Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension

A classical result in online learning characterizes the optimal mistake ...

0 Yuval Filmus, et al. ∙

research

∙ 02/14/2023

Non-stationary Contextual Bandits and Universal Learning

We study the fundamental limits of learning in contextual bandits, where...

0 Moise Blanchard, et al. ∙

research

∙ 12/31/2022

Contextual Bandits and Optimistically Universal Learning

We consider the contextual bandit problem on general action and context ...

0 Moise Blanchard, et al. ∙

research

∙ 10/06/2022

On Optimal Learning Under Targeted Data Poisoning

Consider the task of learning a hypothesis class ℋ in the presence of an...

0 Steve Hanneke, et al. ∙

research

∙ 09/15/2022

Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization

We present a minimax optimal learner for the problem of learning predict...

0 Omar Montasser, et al. ∙

research

∙ 08/31/2022

Fine-Grained Distribution-Dependent Learning Curves

Learning curves plot the expected error of a learning algorithm as a fun...

0 Olivier Bousquet, et al. ∙

research

∙ 06/26/2022

Adversarially Robust Learning of Real-Valued Functions

We study robustness to test-time adversarial attacks in the regression s...

0 Idan Attias, et al. ∙

research

∙ 03/11/2022

Universally Consistent Online Learning with Arbitrarily Dependent Responses

This work provides an online learning rule that is universally consisten...

0 Steve Hanneke, et al. ∙

research

∙ 03/08/2022

Robustly-reliable learners under poisoning attacks

Data poisoning attacks, in which an adversary corrupts a training set wi...

1 Maria-Florina Balcan, et al. ∙

research

∙ 02/11/2022

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability

We study the problem of semi-supervised learning of an adversarially-rob...

0 Idan Attias, et al. ∙

research

∙ 01/21/2022

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

We resolve an open problem of Hanneke on the subject of universally cons...

0 Moise Blanchard, et al. ∙

research

∙ 10/20/2021

Transductive Robust Learning Guarantees

We study the problem of adversarially robust learning in the transductiv...

0 Omar Montasser, et al. ∙

research

∙ 07/20/2021

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

This open problem asks whether there exists an online learning algorithm...

0 Steve Hanneke, et al. ∙

research

∙ 07/18/2021

A Theory of PAC Learnability of Partial Concept Classes

We extend the theory of PAC learning in a way which allows to model a ri...

17 Noga Alon, et al. ∙

research

∙ 03/01/2021

Robust learning under clean-label attack

We study the problem of robust learning under clean-label data-poisoning...

13 Avrim Blum, et al. ∙

research

∙ 02/03/2021

Adversarially Robust Learning with Unknown Perturbation Sets

We study the problem of learning predictors that are robust to adversari...

0 Omar Montasser, et al. ∙

research

∙ 02/02/2021

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

Which classes can be learned properly in the online model? – that is, by...

0 Steve Hanneke, et al. ∙

research

∙ 11/09/2020

A Theory of Universal Learning

How quickly can a given class of concepts be learned from examples? It i...

0 Olivier Bousquet, et al. ∙

research

∙ 10/22/2020

Reducing Adversarially Robust Learning to Non-Robust PAC Learning

We study the problem of reducing adversarially robust learning to standa...

0 Omar Montasser, et al. ∙

research

∙ 06/29/2020

A No-Free-Lunch Theorem for MultiTask Learning

Multitask learning and related areas such as multi-source domain adaptat...

0 Steve Hanneke, et al. ∙

research

∙ 05/24/2020

Proper Learning, Helly Number, and an Optimal SVM Bound

The classical PAC sample complexity bounds are stated for any Empirical ...

0 Olivier Bousquet, et al. ∙

research

∙ 02/12/2020

On the Value of Target Data in Transfer Learning

We aim to understand the value of additional labeled or unlabeled target...

0 Steve Hanneke, et al. ∙

research

∙ 06/24/2019

Universal Bayes consistency in metric spaces

We show that a recently proposed 1-nearest-neighbor-based multiclass lea...

0 Steve Hanneke, et al. ∙

research

∙ 02/12/2019

VC Classes are Adversarially Robustly Learnable, but Only Improperly

We study the question of learning an adversarially robust predictor. We ...

0 Omar Montasser, et al. ∙

research

∙ 10/03/2018

Agnostic Sample Compression for Linear Regression

We obtain the first positive results for bounded sample compression in t...

0 Steve Hanneke, et al. ∙

research

∙ 05/21/2018

Sample Compression for Real-Valued Learners

We give an algorithmically efficient version of the learner-to-compressi...

0 Steve Hanneke, et al. ∙

research

∙ 05/21/2018

A New Lower Bound for Agnostic Learning with Sample Compression Schemes

We establish a tight characterization of the worst-case rates for the ex...

0 Steve Hanneke, et al. ∙

research

∙ 02/20/2018

Actively Avoiding Nonsense in Generative Models

A generative model may generate utter nonsense when it is fit to maximiz...

0 Steve Hanneke, et al. ∙

research

∙ 06/05/2017

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

This work initiates a general study of learning and generalization witho...

0 Steve Hanneke, et al. ∙

research

∙ 04/29/2017

Learning with Changing Features

In this paper we study the setting where features are added or change in...

0 Amit Dhurandhar, et al. ∙

research

∙ 12/26/2015

Statistical Learning under Nonstationary Mixing Processes

We study a special case of the problem of statistical learning without t...

0 Steve Hanneke, et al. ∙

research

∙ 12/22/2015

Refined Error Bounds for Several Learning Algorithms

This article studies the achievable guarantees on the error rates of cer...

0 Steve Hanneke, et al. ∙

research

∙ 07/02/2015

The Optimal Sample Complexity of PAC Learning

This work establishes a new upper bound on the number of samples suffici...

0 Steve Hanneke, et al. ∙

research

∙ 10/03/2014

Minimax Analysis of Active Learning

This work establishes distribution-free upper and lower bounds on the mi...

0 Steve Hanneke, et al. ∙

research

∙ 04/05/2014

A Compression Technique for Analyzing Disagreement-Based Active Learning

We introduce a new and improved characterization of the label complexity...

0 Yair Wiener, et al. ∙

research

∙ 07/16/2012

Surrogate Losses in Passive and Active Learning

Active learning is a type of sequential design for supervised machine le...

0 Steve Hanneke, et al. ∙

research

∙ 08/08/2011

Activized Learning: Transforming Passive to Active with Improved Label Complexity

We study the theoretical advantages of active learning over passive lear...

0 Steve Hanneke, et al. ∙

Steve Hanneke

Featured Co-authors