New homepage: https://sites.google.com/site/yevgenyseldin
- Research Scientist, Max Planck Insitute for Intelligent Systems (Oct 2009 - present)
- Honorary Research Associate, Department of Computer Science, University College London (Aug 2011 - present)
I did my Ph.D. at the Hebrew University of Jerusalem under supervision of Prof. Naftali Tishby.
Machine Learning, Reinforcement Learning, Information Theory.
My current research is focused on data-dependent analysis of reinforcement learning (via application of PAC-Bayesian analysis).
I am also taking part in CompLACS research project.
- PAC-Bayesian Analysis and Its Applications (together with François Laviolette and John Shawe-Taylor). Given at ECML-PKDD-2012.
- PAC-Bayesian Analysis in Supervised, Unsupervised, and Reinforcement Learning (together with François Laviolette and John Shawe-Taylor). Given at ICML-2012.
Events that I organized:
- Multi-Trade-offs in Machine Learning workshop at NIPS-2012 (together with Guy Lever, John Shawe-Taylor, Nicolò Cesa-Bianchi, Koby Crammer, François Laviolette, Gábor Lugosi, and Peter Bartlett).
- New Frontiers in Model Order Selection workshop at NIPS-2011 (together with Koby Crammer, Nicolò Cesa-Bianchi, François Laviolette, and John Shawe-Taylor).
- Empirical Inference Symposium in honor of the 75th anniversary of Prof. Vladimir N. Vapnik (together with Bernhard Schölkopf and Krikamol Muandet).
- Teaching Assistant (frontal) in Introduction to Machine Learning course at The Hebrew University of Jerusalem. Fall 2007 and 2008.
- Teaching Assistant (frontal) in Introduction to Linear Systems course at The Hebrew University of Jerusalem. Spring 2006, 2007, 2008, and 2009.
A quick guide to my main publications:
- PAC-Bayesian analysis of martingales and its application to multiarmed bandits with side information: Please, see our PAC-Bayesian Inequalities for Martingales draft for general PAC-Bayesian inequalities for martingales (joint work with François Laviolette, Nicolò Cesa-Bianchi, John Shawe-Taylor, and Peter Auer, accepted to IEEE Transactions on Information Theory). These inequalities make it possible to control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. We apply these inequalities to multiarmed bandits with side information in PAC-Bayesian Analysis of Contextual Bandits NIPS-2011 paper (joint work with Peter Auer, François Laviolette, John Shawe-Taylor, and Ronald Ortner). Our analysis allows to provide the algorithm large amount of side information, let the algorithm to decide which side information is relevant for the task, and penalize the algorithm only for the side information that it is using de facto. We also provide an algorithm for multiarmed bandits with side information with computational complexity that is independent of the amount of side information and linear in the number of actions.
- PAC-Bayesian analysis of co-clustering, matrix tri-factorization and graphical models: This series of works is best summarized in our JMLR paper PAC-Bayesian Analysis of Co-clustering and Beyond (joint work with Naftali Tishby). We derive generalization bounds and regularized optimization algorithms for co-clustering and matrix tri-factorization. The obtained generalization bounds for co-clustering suggest that co-clustering should optimize a trade-off between empirical data fit and the mutual information that clusters preserve on row and column variables. To the best of our knowledge, this is the first known generalization analysis of co-clustering and matrix tri-factorization and the first time regularization terms are derived for these problems. Our approach to formulating unsupervised learning problems as prediction problems can be extended to virtually any unsupervised learning task and our generalization bounds can be further extended to tree-shaped graphical models.
- Multilevel models for image processing: We were one of the first to apply multilevel unsupervised learning in image analysis, where the first level identified a "dictionary" of common textures within a collection of images and the second level used this dictionary to perform joint unsupervised segmentation of the images. See our Unsupervised Clustering of Images using their Joint Segmentation by Yevgeny Seldin, Sonia Starik and Michael Werman.
- Unsupervised sequence segmentation by mixtures of variable memory Markov sources: We designed an algorithm for unsupervised segmentation of sequences into alternating variable memory Markov sources (implemented as Prediction Suffix Trees). The algorithm was shown to be successful in identification of domains in protein sequences. See our Bioinformatics publication Markovian domain fingerprinting: statistical segmentation of protein sequences by Gill Bejerano, Yevgeny Seldin, Hanah Margalit and Naftali Tishby for the summary of the biological results and ICML-2001 paper Unsupervised Sequence Segmentation by a Mixture of Switching Variable Memory Markov Sources by Yevgeny Seldin, Gill Bejerano, and Naftali Tishby for more details about the algorithm.
Y. Seldin, C. Szepesvári, P. Auer, Y. Abbasi-Yadkori
(2013). Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments In: Proceedings of the Tenth European Workshop on Reinforcement Learning , (Ed) MP Deisenroth and C Szepesvári and J Peters, JMLR, 103-116, EWRL 2012
Y. Seldin, N. Cesa-Bianchi, P. Auer, F. Laviolette, J. Shawe-Taylor
(2012). PAC-Bayes-Bernstein Inequality for Martingales and its Application to Multiarmed Bandits In: JMLR Workshop and Conference Proceedings 26, JMLR, Cambridge, MA, USA, 98-111, On-line Trading of Exploration and Exploitation 2
Y. Seldin, P. Auer, F. Laviolette, J. Shawe-Taylor, R. Ortner
(2011). PAC-Bayesian Analysis of Contextual Bandits In: Advances in Neural Information Processing Systems 24, (Ed) J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger, 1683-1691, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011)
Y. Seldin, N. Tishby
(2009). A PAC-Bayesian Approach to Formulation of Clustering Objectives Proceedings of the NIPS 2009 Workshop "Clustering: Science or Art? Towards Principled Approaches", 1-4, NIPS 2009 Workshop "Clustering: Science or Art? Towards Principled Approaches"
Y. Seldin, N. Tishby
(2009). PAC-Bayesian Generalization Bound for Density Estimation with Application to Co-clustering In: JMLR Workshop and Conference Proceedings Volume 5: AISTATS 2009, In the proceedings of the 12th International Conference on Artificial Intelligence and Statistics (AISTATS 2009), MIT Press, Cambridge, MA, USA, 472-479, 12th International Conference on Artificial Intelligence and Statistics
Y. Seldin, N. Slonim, N. Tishby
(2007). Information Bottleneck for Non Co-Occurrence Data In: Advances in Neural Information Processing Systems 19, (Ed) Schölkopf, B. , J. Platt, T. Hofmann, In Advances in Neural Information Processing Systems 19, 2007 (NIPS 2006), MIT Press, Cambridge, MA, USA, 1241-1248, ISBN: 0-262-19568-2, Twentieth Annual Conference on Neural Information Processing Systems (NIPS 2006)
Y. Seldin, S. Starik, M. Werman
(2003). Unsupervised Clustering of Images using their Joint Segmentation The 3rd International Workshop on Statistical and Computational Theories of Vision (SCTV 2003), 1-24, 3rd International Workshop on Statistical and Computational Theories of Vision (SCTV 2003)
Y. Seldin, G. Bejerano, N. Tishby
(2001). Unsupervised Segmentation and Classification of Mixtures of Markovian Sources The 33rd Symposium on the Interface of Computing Science and Statistics (Interface 2001 - Frontiers in Data Mining and Bioinformatics), 1-15, 33rd Symposium on the Interface of Computing Science and Statistics (Interface 2001 - Frontiers in Data Mining and Bioinformatics)
Y. Seldin, G. Bejerano, N. Tishby
(2001). Unsupervised Sequence Segmentation by a Mixture of Switching Variable Memory Markov Sources In the proceeding of the 18th International Conference on Machine Learning (ICML 2001), 513-520, 18th International Conference on Machine Learning (ICML 2001)