Steve Hanneke
Contact Information:
Email: steve.hanneke@gmail.com
Purdue Office: 2116K Lawson
Address:
Computer Science Department
Purdue University
West Lafayette, IN 47907 USA
I am an Assistant Professor in the Computer Science Department at Purdue University.
I work on topics in statistical learning theory.
Research Interests:
My general research interest is in systems that can improve their performance with experience, a topic known as machine learning. My focus is on the statistical analysis of machine learning. The essential questions I am interested in answering are “what can be learned from empirical observation / experimentation,” and “how much observation / experimentation is necessary and sufficient to learn it?”
This overall topic intersects with several academic disciplines, including statistical learning theory, artificial intelligence, statistical inference, algorithmic and statistical information theories, probability theory, philosophy of science, and epistemology.
About me:
I am an Assistant Professor in the Computer Science Department at Purdue University.
Prior to joining Purdue, I was a Research Assistant Professor at the Toyota Technological Institute at Chicago (TTIC) 20182021, and was an independent scientist working in Princeton 20122018, aside from a brief onesemester stint as a Visiting Lecturer at Princeton University in 2018.
Before that, from 2009 to 2012, I was a Visiting Assistant Professor in the Department of Statistics at
Carnegie Mellon University,
also affiliated with the Machine Learning Department.
I received my PhD in 2009 from the
Machine Learning Department at
Carnegie Mellon University,
coadvised by Eric Xing
and Larry Wasserman.
My thesis work was on the theoretical foundations of active learning.
From 2002 to 2005, I was an undergraduate studying
Computer Science
at the University of Illinois at UrbanaChampaign
(UIUC),
where I worked on semisupervised learning with Prof.
Dan Roth
and the students in the Cognitive Computation Group.
Prior to that, I studied Computer Science at Webster University
in St. Louis, MO,
where I played around with neural networks
and classic AI a bit.
Note: A speaker bio for presentations can be found here.
Recent News and Activities:
 Our paper Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games was runner up for the COLT 2021 Best Paper Award.
 Fall 2021 I have joined Purdue University as an Assistant Professor in Computer Science.
 Received the Best Paper Award at ALT 2021 for our paper “Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound”.
 New manuscript “A Theory of Universal Learning” posted to the arXiv.
 Received the Best Paper Award at COLT 2020 for our paper “Proper Learning, Helly Number, and an Optimal SVM Bound”.
 Presented (with Rob Nowak) an ICML 2019 Tutorial on Active Learning: From Theory to Practice. [slides]
 Organized the ALT 2019 workshop: When Smaller Sample Sizes Suffice for Learning.
 Our paper VC Classes are Adversarially Robustly Learnable, but Only Improperly received a Best Student Paper Award at COLT 2019.
 Fall 2018 I joined the Toyota Technological Institute at Chicago (TTIC) as a Research Assistant Professor.
 Spring 2018 I taught ORF 525 “Statistical Learning and Nonparametric Estimation” at Princeton University.
 My ICML 2007 paper “A Bound on the Label Complexity of Agnostic Active Learning” received Honorable Mention for the ICML 2017 Test of Time Award.
 Program Committee Chair (with Lev Reyzin) for the 28^{th} International Conference on Algorithmic Learning Theory (ALT 2017), held October 1517 in Kyoto, Japan. See our published proceedings.
 New manuscript “Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes” posted to the arXiv.
Teaching:
Purdue University:
Fall 2022: CS 59300MLT, Machine Learning Theory.
Spring 2022, 2023: CS 37300, Data Mining and Machine Learning.
Fall 2021: CS 59200MLT, Machine Learning Theory.
Princeton University:
Spring 2018: ORF 525, Statistical Learning and Nonparametric Estimation.
Carnegie Mellon University:
Spring 2012: 36752, Advanced Probability Overview.
Fall 2011: 36755, Advanced Statistical Theory I.
Spring 2011: 36752, Advanced Probability Overview.
Fall 2010 Mini 1: 36781, Advanced Statistical Methods I: Active Learning
Fall 2010 Mini 2: 36782, Advanced Statistical Methods II: Advanced Topics in Machine Learning Theory
Spring 2010:
36754, Advanced Probability II: Stochastic Processes.
Fall 2009: 36752, Advanced Probability Overview.
A Survey of Theoretical Active Learning:
Theory of Active Learning.
[pdf][ps]
This is a survey of some of the recent advances in the theory of active learning, with particular emphasis on label complexity guarantees for disagreementbased methods.
The current version (v1.1) was updated on September 22, 2014.
A few recent significant advances in active learning not yet covered in the survey:
[ZC14], [WHEY15], [HY15].
An abbreviated version of this survey appeared in the Foundations and Trends in Machine Learning series,
Volume 7, Issues 23, 2014.
Selected Recent Works:
 Alon, N., Hanneke, S., Holzman, R., and Moran, S. (2021). A Theory of PAC Learnability of Partial Concept Classes. In Proceedings of the 62^{nd} Annual Symposium on Foundations of Computer Science (FOCS).
 Hanneke, S. (2021). Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes. Journal of Machine Learning Research, Vol. 22 (130), pp. 1116.
 Hanneke, S., Livni, R., and Moran, S. (2021). Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games. In Proceedings of the 34^{th} Annual Conference on Learning Theory (COLT).
 Bousquet, O., Hanneke, S., Moran, S., van Handel, R., and Yehudayoff, A. (2021). A Theory of Universal Learning. In Proceedings of the 53^{rd} Annual ACM Symposium on Theory of Computing (STOC).
 Bousquet, O., Hanneke, S., Moran, S., and Zhivotovskiy, N. (2020). Proper Learning, Helly Number, and an Optimal SVM Bound. In Proceedings of the 33^{rd} Annual Conference on Learning Theory (COLT).
 Montasser, O., Hanneke, S., and Srebro, N. (2019). VC Classes are Adversarially Robustly Learnable, but Only Improperly. In Proceedings of the 32^{nd} Annual Conference on Learning Theory (COLT).
 Hanneke, S. (2016). The Optimal Sample Complexity of PAC Learning. Journal of Machine Learning Research, Vol. 17 (38), pp. 115.
 Hanneke, S. and Yang, L. (2015). Minimax Analysis of Active Learning. Journal of Machine Learning Research, Vol. 16 (12), pp. 34873602.
 Hanneke, S. (2012). Activized Learning: Transforming Passive to Active with Improved Label Complexity. Journal of Machine Learning Research, Vol. 13 (5), pp. 14691587.
Articles in Preparation:
 Nonparametric Active Learning, Part 1: Smooth Regression Functions. [pdf][ps].
 Nonparametric Active Learning, Part 2: Smooth Decision Boundaries.
 Active Learning with Identifiable Mixture Models. Joint work with Vittorio Castelli and Liu Yang.
 Bousquet, O., Hanneke, S., Moran, S., Shafer, J., and Tolstikhin, I. (2022). FineGrained DistributionDependent Learning Curves. [pdf][arXiv].
 Attias, I. and Hanneke, S. (2022). Adversarially Robust Learning of RealValued Functions. [pdf][arXiv].
 Blanchard, M., Hanneke, S., and Jaillet, P. (2023). Contextual Bandits and Optimistically Universal Learning. [pdf][arXiv].
 Hanneke, S., Kontorovich, A., and Kornowski, G. (2023). Nearoptimal learning with average HÃ¶lder smoothness. [pdf][arXiv].
 Blanchard, M., Hanneke, S., and Jaillet, P. (2023). Nonstationary Contextual Bandits and Universal Learning. [pdf][arXiv].
 Filmus, Y., Hanneke, S., Mehalel, I., and Moran, S. (2023) Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension. [pdf][arXiv].
All Publications:
(authors are listed in alphabetical order, except sometimes when a student author is listed first).
2022
 Hanneke, S., Karbasi, A., Moran, S., and Velegkas, G. (2022). Universal Rates for Interactive Learning. Advances in Neural Information Processing Systems 36 (NeurIPS).
 Montasser, O., Hanneke, S., and Srebro, N. (2022). Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization. Advances in Neural Information Processing Systems 36 (NeurIPS). [pdf][arXiv].
 Hanneke, S., Karbasi, A., Mahmoody, M., Mehalel, I., and Moran, S. (2022). On Optimal Learning Under Targeted Data Poisoning. Advances in Neural Information Processing Systems 36 (NeurIPS). [pdf][arXiv]
 Attias, I., Hanneke, S., and Mansour, Y. (2022). A Characterization of SemiSupervised AdversariallyRobust PAC Learnability. Advances in Neural Information Processing Systems 36 (NeurIPS). [pdf][arXiv].
 Balcan, M.F., Blum, A., Hanneke, S., and Sharma, D. (2022). Robustlyreliable Learners Under Poisoning Attacks. In Proceedings of the 35^{th} Annual Conference on Learning Theory (COLT). [pdf][arXiv][official page].
 Hanneke, S. and Kpotufe, S. (2022). A NoFreeLunch Theorem for MultiTask Learning. The Annals of Statistics. Vol. 50 (6), pp. 31193143. [pdf][arXiv][journal page]
 Hanneke, S. (2022). Universally consistent online learning with arbitrarily dependent responses. In Proceedings of the 33^{rd} International Conference on Algorithmic Learning Theory (ALT). [pdf][arXiv].
 Blanchard, M., Cosson, R., and Hanneke, S. (2022). Universal Online Learning with Unbounded Losses: Memory Is All You Need. In Proceedings of the 33^{rd} International Conference on Algorithmic Learning Theory (ALT). [pdf][arXiv].
 Montasser, O., Hanneke, S., and Srebro, N. (2022). Transductive Robust Learning Guarantees. In Proceedings of the 25^{th} International Conference on Artificial Intelligence and Statistics (AISTATS). [pdf][arXiv].
2021
 Alon, N., Hanneke, S., Holzman, R., and Moran, S. (2021). A Theory of PAC Learnability of Partial Concept Classes. In Proceedings of the 62^{nd} Annual Symposium on Foundations of Computer Science (FOCS). [pdf][arXiv]

Hanneke, S., Livni, R., and Moran, S. (2021).
Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Games. In Proceedings of the 34^{th} Annual Conference on Learning Theory (COLT).
[pdf][arXiv][official page][videos]
Runner up for the Best Paper Award.  Montasser, O., Hanneke, S., and Srebro, N. (2021). Adversarially Robust Learning with Unknown Perturbation Sets. In Proceedings of the 34^{th} Annual Conference on Learning Theory (COLT). [pdf][arXiv][official page][videos]
 Blum, A., Hanneke, S., Qian, J., and Shao, H. (2021). Robust Learning under CleanLabel Attack. In Proceedings of the 34^{th} Annual Conference on Learning Theory (COLT). [pdf][arXiv][official page][videos]
 Hanneke, S. (2021). Open Problem: Is There an Online Learning Algorithm That Learns Whenever Online Learning Is Possible?. In Proceedings of the 34^{th} Annual Conference on Learning Theory (COLT). [pdf][arXiv][official page][videos]
 Bousquet, O., Hanneke, S., Moran, S., van Handel, R., and Yehudayoff, A. (2021). A Theory of Universal Learning. In Proceedings of the 53^{rd} Annual ACM Symposium on Theory of Computing (STOC). [pdf][official page][arXiv]
 Hanneke, S. (2021). Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes. Journal of Machine Learning Research. Vol. 22 (130), pp. 1116. [pdf][arXiv][journal page]
 Hanneke, S. and Yang, L. (2021). Toward a General Theory of Online Selective Sampling: Trading Off Mistakes and Queries. In Proceedings of the 24^{th} International Conference on Artificial Intelligence and Statistics (AISTATS). [pdf][official page]

Hanneke, S. and Kontorovich, A. (2021).
Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound.
In Proceedings of the 32^{nd} International Conference on Algorithmic Learning Theory (ALT).
[pdf][official page][arXiv]
Winner of the Best Paper Award.  Hanneke, S., Kontorovich, A., Sabato, S., and Weiss, R. (2021). Universal Bayes Consistency in Metric Spaces. The Annals of Statistics, Vol. 49 (4), pp. 21292150. [pdf][arXiv][official page]
2020
 Montasser, O., Hanneke, S. and Srebro, N. (2020). Reducing Adversarially Robust Learning to NonRobust PAC Learning. Advances in Neural Information Processing Systems 34 (NeurIPS). [pdf][official page][arXiv]

Bousquet, O., Hanneke, S., Moran, S., and Zhivotovskiy, N. (2020).
Proper Learning, Helly Number, and an Optimal SVM Bound.
In Proceedings of the 33^{rd} Annual Conference on Learning Theory (COLT).
[pdf][official page][arXiv]
Winner of the Best Paper Award.
2019
 Hanneke, S. and Yang, L. (2019). Surrogate Losses in Passive and Active Learning. Electronic Journal of Statistics, Vol. 13 (2), pp. 46464708. [pdf][ps][journal page][arXiv].
 Hanneke, S. and Kpotufe, S. (2019). On the Value of Target Data in Transfer Learning. Advances in Neural Information Processing Systems 33 (NeurIPS). [pdf][official page][arXiv].
 Hanneke, S. and Kontorovich, A. (2019). Optimality of SVM: Novel Proofs and Tighter Bounds. Theoretical Computer Science. Volume 796, Pages 99113. [pdf][journal page]

Montasser, O., Hanneke, S., and Srebro, N. (2019).
VC Classes are Adversarially Robustly Learnable, but Only Improperly.
In Proceedings of the 32^{nd} Annual Conference on Learning Theory (COLT).
[pdf][official page][arXiv]
Winner of a Best Student Paper Award.  Hanneke, S. and Kontorovich, A. (2019). A Sharp Lower Bound for Agnostic Learning with Sample Compression Schemes. In Proceedings of the 30^{th} International Conference on Algorithmic Learning Theory (ALT). [pdf][official page][arXiv]
 Hanneke, S., Kontorovich, A., and Sadigurschi, M. (2019). Sample Compression for RealValued Learners. In Proceedings of the 30^{th} International Conference on Algorithmic Learning Theory (ALT). [pdf][official page][arXiv]
 Hanneke, S. and Yang, L. (2019). Statistical Learning under Nonstationary Mixing Processes. In Proceedings of the 22^{nd} International Conference on Artificial Intelligence and Statistics (AISTATS). [pdf][official page][arXiv]
2018
 Hanneke, S. and Yang, L. (2018). Testing Piecewise Functions. Theoretical Computer Science, Vol. 745, pp. 2335. [pdf][ps][journal page][arXiv]

Zhivotovskiy, N. and Hanneke, S. (2018). Localization of VC Classes: Beyond Local Rademacher Complexities.
Theoretical Computer Science, Vol. 742, pp. 2749.
[pdf][journal page][arXiv]
(Special Issue for ALT 2016; Invited)  Hanneke, S., Kalai, A., Kamath, G., and Tzamos, C. (2018). Actively Avoiding Nonsense in Generative Models. In Proceedings of the 31^{st} Annual Conference on Learning Theory (COLT). [pdf][official page][arXiv]

Yang, L., Hanneke, S., and Carbonell, J. (2018).
Bounds on the Minimax Rate for Estimating a Prior over a VC Class from Independent Learning Tasks.
Theoretical Computer Science, Vol. 716, pp. 124140.
[pdf][ps][journal page][arXiv]
(Special Issue for ALT 2015; Invited)
2016
 Zhivotovskiy, N. and Hanneke, S. (2016). Localization of VC Classes: Beyond Local Rademacher Complexities. In Proceedings of the 27^{th} International Conference on Algorithmic Learning Theory (ALT). [pdf][ps][arXiv]
 Hanneke, S. (2016). Refined Error Bounds for Several Learning Algorithms. Journal of Machine Learning Research, Vol. 17 (135), pp. 155. [pdf][ps][arXiv][journal page]
 Hanneke, S. (2016). The Optimal Sample Complexity of PAC Learning. Journal of Machine Learning Research, Vol. 17 (38), pp. 115. [pdf][ps][arXiv][journal page]
2015
 Hanneke, S. and Yang, L. (2015). Minimax Analysis of Active Learning. Journal of Machine Learning Research, Vol. 16 (12), pp. 34873602. [pdf][ps][arXiv][journal page]

Hanneke, S., Kanade, V., and Yang, L. (2015).
Learning with a Drifting Target Concept.
In Proceedings of the 26^{th} International Conference on Algorithmic Learning Theory (ALT).
[pdf][ps][arXiv]
See also this note on a result for the sample complexity of efficient agnostic learning implicit in the above concept drift paper: [pdf]  Yang, L., Hanneke, S., and Carbonell, J. (2015). Bounds on the Minimax Rate for Estimating a Prior over a VC Class from Independent Learning Tasks. In Proceedings of the 26^{th} International Conference on Algorithmic Learning Theory (ALT). [pdf][ps][arXiv]
 Wiener, Y., Hanneke, S., and ElYaniv, R. (2015). A Compression Technique for Analyzing DisagreementBased Active Learning. Journal of Machine Learning Research, Vol. 16 (4), pp. 713745. [pdf][ps][arXiv][journal page]
2014

Hanneke, S. (2014).
Theory of DisagreementBased Active Learning.
Foundations and Trends in Machine Learning, Vol. 7 (23), pp. 131309.
[official][Amazon]
There is also an extended version, which I may update from time to time.
2013
 Yang, L. and Hanneke, S. (2013). Activized Learning with Uniform Classification Noise. In Proceedings of the 30^{th} International Conference on Machine Learning (ICML). [pdf][ps][appendix pdf][appendix ps]
 Yang, L., Hanneke, S., and Carbonell, J. (2013). A Theory of Transfer Learning with Applications to Active Learning. Machine Learning, Vol. 90 (2), pp. 161189. [pdf][ps][journal page]
2012
 Balcan, M.F. and Hanneke, S. (2012). Robust Interactive Learning. In Proceedings of the 25^{th} Annual Conference on Learning Theory (COLT). [pdf][ps][arXiv]

Hanneke, S. (2012).
Activized Learning: Transforming Passive to Active with Improved Label Complexity.
Journal of Machine Learning Research, Vol. 13 (5), pp. 14691587.
[pdf][ps][arXiv][journal page]
Related material: extended abstract, Chapter 4 in my thesis, and various presentations [slides].
2011
 Yang, L., Hanneke, S., and Carbonell, J. (2011). Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning. In Proceedings of the 24^{th} Annual Conference on Learning Theory (COLT).[pdf][ps]
 Yang, L., Hanneke, S., and Carbonell, J. (2011). The Sample Complexity of SelfVerifying Bayesian Active Learning. In Proceedings of the 14^{th} International Conference on Artificial Intelligence and Statistics (AISTATS).[pdf][ps]
 Hanneke, S. (2011). Rates of Convergence in Active Learning. The Annals of Statistics, Vol. 39 (1), pp. 333361. [pdf][ps][journal page]
2010

Yang, L., Hanneke, S., and Carbonell, J. (2010).
Bayesian Active Learning Using Arbitrary Binary Valued Queries.
In Proceedings of the 21^{st} International Conference on Algorithmic Learning Theory (ALT).[pdf][ps]
Also available in information theory jargon. [pdf][ps]  Hanneke, S., Fu, W., and Xing, E.P. (2010). Discrete Temporal Models of Social Networks. The Electronic Journal of Statistics, Vol. 4, pp. 585605. [pdf][journal page]
 Hanneke, S. and Yang, L. (2010). Negative Results for Active Learning with Convex Losses. Proceedings of the 13^{th} International Conference on Artificial Intelligence and Statistics (AISTATS). [pdf][ps]

Balcan, M.F., Hanneke, S., and Wortman Vaughan, J. (2010).
The True Sample Complexity of Active Learning.
Machine Learning, Vol. 80 (23), pp. 111139.
[pdf][ps][journal page]
(Special Issue for COLT 2008; Invited)
2009
 Hanneke, S. (2009). Theoretical Foundations of Active Learning. Doctoral Dissertation. Machine Learning Department. Carnegie Mellon University. [pdf][ps][defense slides]

Hanneke, S. (2009).
Adaptive Rates of Convergence in Active Learning.
In Proceedings of the 22^{nd} Annual Conference on Learning Theory (COLT).[pdf][ps][slides]
Also available in expanded journal version.  Hanneke, S. and Xing, E. P. (2009). Network Completion and Survey Sampling. In Proceedings of the 12^{th} International Conference on Artificial Intelligence and Statistics (AISTATS). [pdf][ps][slides]
2008

Balcan, M.F., Hanneke, S., and Wortman, J. (2008).
The True Sample Complexity of Active Learning.
In Proceedings of the 21^{st} Annual Conference on Learning Theory (COLT).
[pdf][ps][slides]
Winner of the Mark Fulk Best Student Paper Award.
Also available in an extended journal version.
2007

Balcan, M.F., EvenDar, E., Hanneke, S., Kearns, M., Mansour, Y., and Wortman, J. (2007).
Asymptotic Active Learning.
NIPS Workshop on Principles of Learning Problem Design.
[pdf][ps][spotlight slide]
Also available in improved conference version and expanded journal version. 
Hanneke, S. and Xing, E. P. (2007).
Network Completion and Survey Sampling.
NIPS Workshop on Statistical Network Models.
See our later conference publication.  Hanneke, S. (2007). Teaching Dimension and the Complexity of Active Learning. In proceedings of the 20^{th} Annual Conference on Learning Theory (COLT). [pdf][ps][slides]

Hanneke, S. (2007).
A Bound on the Label Complexity of Agnostic Active Learning.
In proceedings of the 24^{th} Annual International Conference on Machine Learning (ICML).
[pdf][ps][slides]
Honorable Mention for the ICML 2017 Test of Time Award. 
Guo, F., Hanneke, S., Fu, W., and Xing, E.P. (2007).
Recovering Temporally Rewiring Networks: A Modelbased Approach.
In proceedings of the 24^{th} Annual International Conference on Machine Learning (ICML).
[pdf]
Also see our related earlier work. 
Hanneke, S. (2007).
The Complexity of Interactive Machine Learning.
KDD Project Report (aka Master’s Thesis).
Machine Learning Department, Carnegie Mellon University.
[pdf][ps][slides]
Includes some interesting results from a class project on The Cost Complexity of Interactive Learning, in addition to my COLT07 and ICML07 papers.
2006

Hanneke, S. and Xing, E. P. (2006).
Discrete Temporal Models of Social Networks.
In Proceedings of the ICML Workshop on Statistical Network Analysis.
[pdf][ps][slides]
Also available in an extended journal version  Hanneke, S. (2006). An Analysis of Graph Cut Size for Transductive Learning. In Proceedings of the 23^{rd} International Conference on Machine Learning (ICML). [pdf][ps][slides ppt][slides pdf]
Visitors since 11/14/2014.