Steve Hanneke

74 papers · 2010–2025 · 6 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 🏃 Academic Marathon (15) 🐝 Cross-Pollinator (13) 🌉 Interdisciplinary Bridge 🏠 Conference Loyalist (28) 🐺 Lone Wolf (7) 🤝 Dynamic Duo (20) 🔬 Deep Specialist (10) 🏆 Keyword Champion (3) 💎 Century Club (74) 🚀 Conference Pioneer 🔥 Unstoppable (11) ⚡ Prolific Year (15) ❓ The Questioner 🗃️ Keyword Collector (173)

Conferences

COLT (28) NIPS (18) ALT (12) JMLR (6) AISTATS (5) ICML (5)

Top co-authors

Shay Moran (20) Liu Yang (9) Aryeh Kontorovich (6) Idan Attias (6) Omar Montasser (5) Amin Karbasi (5) Amirreza Shaeiri (4) Grigoris Velegkas (4) Amir Yehudayoff (3) Avrim Blum (3)

Keywords

online learning (13) pac learning (13) vc dimension (12) sample complexity (12) active learning (10) learning theory (10) littlestone dimension (8) sample compression (7) mistake bound (7) concept class (7) agnostic learning (5) uniform convergence (5) adversarial robustness (5) multiclass classification (5) adversarial learning (4) learning curve (4) learning rate (4) query complexity (4) robust learning (4) universal learning (4)

Papers

Reliable Active Apprenticeship Learning ALT 2025

For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent ALT 2025

A Complete Characterization of Learnability for Stochastic Noisy Bandits ALT 2025

Representation Preserving Multiclass Agnostic to Realizable Reduction ICML 2025

Proofs as Explanations: Short Certificates for Reliable Predictions COLT 2025

Sample Compression Scheme Reductions ALT 2025

Open Problem: Data Selection for Regression Tasks COLT 2025

A Trichotomy for List Transductive Online Learning ICML 2025

Private List Learnability vs. Online List Learnability COLT 2025

Universal Rates for Multiclass Learning with Bandit Feedback COLT 2025

Universal Rates of ERM for Agnostic Learning COLT 2025

Data Selection for ERMs COLT 2025

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs NIPS 2024

Agnostic Sample Compression Schemes for Regression ICML 2024

Improved Sample Complexity for Multiclass PAC Learning NIPS 2024

Multiclass Transductive Online Learning NIPS 2024

The Dimension of Self-Directed Learning ALT 2024

Efficient Agnostic Learning with Average Smoothness ALT 2024

Open problem: Direct Sums in Learning Theory COLT 2024

List Sample Compression and Uniform Convergence COLT 2024

The Star Number and Eluder Dimension: Elementary Observations About the Dimensions of Disagreement COLT 2024

Dual VC Dimension Obstructs Sample Compression by Embeddings COLT 2024

Universal Rates for Regression: Separations between Cut-Off and Absolute Loss COLT 2024

A Theory of Optimistically Universal Online Learnability for General Concept Classes NIPS 2024

Universal Rates for Active Learning NIPS 2024

Learning from Snapshots of Discrete and Continuous Data Streams NIPS 2024

Universal Rates of Empirical Risk Minimization NIPS 2024

Adversarially Robust PAC Learnability of Real-Valued Functions ICML 2023

Bandit Learnability can be Undecidable COLT 2023

Limits of Model Selection under Transfer Learning COLT 2023

Multiclass Online Learning and Uniform Convergence COLT 2023

A Trichotomy for Transductive Online Learning NIPS 2023

Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension COLT 2023

Improper Multiclass Boosting COLT 2023

Universal Rates for Multiclass Learning COLT 2023

Near-optimal learning with average Hölder smoothness NIPS 2023

Optimal Learners for Realizable Regression: PAC Learning and Online Learning NIPS 2023

Reliable learning in challenging environments NIPS 2023

Fine-Grained Distribution-Dependent Learning Curves COLT 2023

Adversarial Resilience in Sequential Prediction via Abstention NIPS 2023

Universally Consistent Online Learning with Arbitrarily Dependent Responses ALT 2022

A Characterization of Semi-Supervised Adversarially Robust PAC Learnability NIPS 2022

Universal Rates for Interactive Learning NIPS 2022

On Optimal Learning Under Targeted Data Poisoning NIPS 2022

Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization NIPS 2022

Transductive Robust Learning Guarantees AISTATS 2022

Universal Online Learning with Unbounded Losses: Memory Is All You Need ALT 2022

Robustly-reliable learners under poisoning attacks COLT 2022

Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible? COLT 2021

Adversarially Robust Learning with Unknown Perturbation Sets COLT 2021

Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games COLT 2021

Robust learning under clean-label attack COLT 2021

Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound ALT 2021

Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries AISTATS 2021

Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes JMLR 2021

Proper Learning, Helly Number, and an Optimal SVM Bound COLT 2020

Reducing Adversarially Robust Learning to Non-Robust PAC Learning NIPS 2020

On the Value of Target Data in Transfer Learning NIPS 2019

Statistical Learning under Nonstationary Mixing Processes AISTATS 2019

A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes ALT 2019

Sample Compression for Real-Valued Learners ALT 2019

VC Classes are Adversarially Robustly Learnable, but Only Improperly COLT 2019

Actively Avoiding Nonsense in Generative Models COLT 2018

Algorithmic Learning Theory (ALT) 2017: Preface ALT 2017

The Optimal Sample Complexity of PAC Learning JMLR 2016

Refined Error Bounds for Several Learning Algorithms JMLR 2016

A Compression Technique for Analyzing Disagreement-Based Active Learning JMLR 2015

Minimax Analysis of Active Learning JMLR 2015

Activized Learning with Uniform Classification Noise ICML 2013

Robust Interactive Learning COLT 2012

Activized Learning: Transforming Passive to Active with Improved Label Complexity JMLR 2012

Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning COLT 2011

The Sample Complexity of Self-Verifying Bayesian Active Learning AISTATS 2011

Negative Results for Active Learning with Convex Losses AISTATS 2010