| 2026 | STOC | Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back. | Alon Cohen, Liad Erez, Steve Hanneke, Tomer Koren, Yishay Mansour, Shay Moran, Qian Zhang |
| 2026 | STOC | On the Learning Curves of Revenue Maximization. | Steve Hanneke, Alkis Kalavasis, Shay Moran, Grigoris Velegkas |
| 2025 | ALT | Sample Compression Scheme Reductions. | Idan Attias, Steve Hanneke, Arvind Ramaswami |
| 2025 | ALT | Reliable Active Apprenticeship Learning. | Steve Hanneke, Liu Yang, Gongju Wang, Yulun Song |
| 2025 | ALT | For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent. | Steve Hanneke, Amirreza Shaeiri, Hongao Wang |
| 2025 | ALT | A Complete Characterization of Learnability for Stochastic Noisy Bandits. | Steve Hanneke, Kun Wang |
| 2025 | COLT | Proofs as Explanations: Short Certificates for Reliable Predictions. | Avrim Blum, Steve Hanneke, Chirag Pabbaraju, Donya Saless |
| 2025 | COLT | Private List Learnability vs. Online List Learnability. | Steve Hanneke, Shay Moran, Hilla Schefler, Iska Tsubari |
| 2025 | COLT | Data Selection for ERMs. | Steve Hanneke, Shay Moran, Alexander Shlimovich, Amir Yehudayoff |
| 2025 | COLT | Open Problem: Data Selection for Regression Tasks. | Steve Hanneke, Shay Moran, Alexander Shlimovich, Amir Yehudayoff |
| 2025 | COLT | Universal Rates for Multiclass Learning with Bandit Feedback. | Steve Hanneke, Amirreza Shaeiri, Qian Zhang |
| 2025 | COLT | Universal Rates of ERM for Agnostic Learning. | Steve Hanneke, Mingyue Xu |
| 2025 | ICML | Representation Preserving Multiclass Agnostic to Realizable Reduction. | Steve Hanneke, Qinglin Meng, Amirreza Shaeiri |
| 2025 | ICML | A Trichotomy for List Transductive Online Learning. | Steve Hanneke, Amirreza Shaeiri |
| 2024 | ALT | The Dimension of Self-Directed Learning. | Pramith Devulapalli, Steve Hanneke |
| 2024 | ALT | Efficient Agnostic Learning with Average Smoothness. | Steve Hanneke, Aryeh Kontorovich, Guy Kornowski |
| 2024 | COLT | Dual VC Dimension Obstructs Sample Compression by Embeddings. | Zachary Chase, Bogdan Chornomaz, Steve Hanneke, Shay Moran, Amir Yehudayoff |
| 2024 | COLT | Universal Rates for Regression: Separations between Cut-Off and Absolute Loss. | Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas |
| 2024 | COLT | The Star Number and Eluder Dimension: Elementary Observations About the Dimensions of Disagreement. | Steve Hanneke |
| 2024 | COLT | List Sample Compression and Uniform Convergence. | Steve Hanneke, Shay Moran, Tom Waknine |
| 2024 | COLT | Open problem: Direct Sums in Learning Theory. | Steve Hanneke, Shay Moran, Tom Waknine |
| 2024 | FOCS | Ramsey Theorems for Trees and a General 'Private Learning Implies Online Learning' Theorem. | Simone Fioravanti, Steve Hanneke, Shay Moran, Hilla Schefler, Iska Tsubari |
| 2024 | FOCS | Revisiting Agnostic PAC Learning. | Steve Hanneke, Kasper Green Larsen, Nikita Zhivotovskiy |
| 2024 | ICML | Agnostic Sample Compression Schemes for Regression. | Idan Attias, Steve Hanneke, Aryeh Kontorovich, Menachem Sadigurschi |
| 2023 | COLT | Fine-Grained Distribution-Dependent Learning Curves. | Olivier Bousquet, Steve Hanneke, Shay Moran, Jonathan Shafer, Ilya O. Tolstikhin |
| 2023 | COLT | Improper Multiclass Boosting. | Nataly Brukhim, Steve Hanneke, Shay Moran |
| 2023 | COLT | Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension. | Yuval Filmus, Steve Hanneke, Idan Mehalel, Shay Moran |
| 2023 | COLT | Bandit Learnability can be Undecidable. | Steve Hanneke, Liu Yang |
| 2023 | COLT | Limits of Model Selection under Transfer Learning. | Steve Hanneke, Samory Kpotufe, Yasaman Mahdaviyeh |
| 2023 | COLT | Multiclass Online Learning and Uniform Convergence. | Steve Hanneke, Shay Moran, Vinod Raman, Unique Subedi, Ambuj Tewari |
| 2023 | COLT | Universal Rates for Multiclass Learning. | Steve Hanneke, Shay Moran, Qian Zhang |
| 2023 | ICML | Adversarially Robust PAC Learnability of Real-Valued Functions. | Idan Attias, Steve Hanneke |
| 2022 | AISTATS | Transductive Robust Learning Guarantees. | Omar Montasser, Steve Hanneke, Nathan Srebro |
| 2022 | ALT | Universal Online Learning with Unbounded Losses: Memory Is All You Need. | Mose Blanchard, Romain Cosson, Steve Hanneke |
| 2022 | ALT | Universally Consistent Online Learning with Arbitrarily Dependent Responses. | Steve Hanneke |
| 2022 | COLT | Robustly-reliable learners under poisoning attacks. | Maria-Florina Balcan, Avrim Blum, Steve Hanneke, Dravyansh Sharma |
| 2021 | AISTATS | Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries. | Steve Hanneke, Liu Yang |
| 2021 | ALT | Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound. | Steve Hanneke, Aryeh Kontorovich |
| 2021 | COLT | Robust learning under clean-label attack. | Avrim Blum, Steve Hanneke, Jian Qian, Han Shao |
| 2021 | COLT | Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible? | Steve Hanneke |
| 2021 | COLT | Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games. | Steve Hanneke, Roi Livni, Shay Moran |
| 2021 | COLT | Adversarially Robust Learning with Unknown Perturbation Sets. | Omar Montasser, Steve Hanneke, Nathan Srebro |
| 2021 | FOCS | A Theory of PAC Learnability of Partial Concept Classes. | Noga Alon, Steve Hanneke, Ron Holzman, Shay Moran |
| 2021 | STOC | A theory of universal learning. | Olivier Bousquet, Steve Hanneke, Shay Moran, Ramon van Handel, Amir Yehudayoff |
| 2020 | COLT | Proper Learning, Helly Number, and an Optimal SVM Bound. | Olivier Bousquet, Steve Hanneke, Shay Moran, Nikita Zhivotovskiy |
| 2020 | ITA | Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes. | Steve Hanneke |
| 2020 | ITA | Universal Bayes Consistency in Metric Spaces. | Steve Hanneke, Aryeh Kontorovich, Sivan Sabato, Roi Weiss |
| 2019 | AISTATS | Statistical Learning under Nonstationary Mixing Processes. | Steve Hanneke, Liu Yang |
| 2019 | ALT | A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes. | Steve Hanneke, Aryeh Kontorovich |
| 2019 | ALT | Sample Compression for Real-Valued Learners. | Steve Hanneke, Aryeh Kontorovich, Menachem Sadigurschi |
| 2019 | COLT | VC Classes are Adversarially Robustly Learnable, but Only Improperly. | Omar Montasser, Steve Hanneke, Nathan Srebro |
| 2018 | COLT | Actively Avoiding Nonsense in Generative Models. | Steve Hanneke, Adam Tauman Kalai, Gautam Kamath, Christos Tzamos |
| 2016 | ALT | Localization of VC Classes: Beyond Local Rademacher Complexities. | Nikita Zhivotovskiy, Steve Hanneke |
| 2015 | ALT | Learning with a Drifting Target Concept. | Steve Hanneke, Varun Kanade, Liu Yang |
| 2015 | ALT | Bounds on the Minimax Rate for Estimating a Prior over a VC Class from Independent Learning Tasks. | Liu Yang, Steve Hanneke, Jaime G. Carbonell |
| 2013 | ICML | Activized Learning with Uniform Classification Noise. | Liu Yang, Steve Hanneke |
| 2010 | ALT | Bayesian Active Learning Using Arbitrary Binary Valued Queries. | Liu Yang, Steve Hanneke, Jaime G. Carbonell |
| 2009 | COLT | Adaptive Rates of Convergence in Active Learning. | Steve Hanneke |
| 2008 | COLT | The True Sample Complexity of Active Learning. | Maria-Florina Balcan, Steve Hanneke, Jennifer Wortman |
| 2007 | COLT | Teaching Dimension and the Complexity of Active Learning. | Steve Hanneke |
| 2007 | ICML | Recovering temporally rewiring networks: a model-based approach. | Fan Guo, Steve Hanneke, Wenjie Fu, Eric P. Xing |
| 2007 | ICML | A bound on the label complexity of agnostic active learning. | Steve Hanneke |
| 2006 | ICML | An analysis of graph cut size for transductive learning. | Steve Hanneke |
| 2006 | ICML | Discrete Temporal Models of Social Networks. | Steve Hanneke, Eric P. Xing |