I have moved to France (Sept., 2016); my new webpage.

Zoltán Szabó: .bib


Google Scholar Citations, LinkedIn, Mendeley, ResearchGate, arXiv (+Atom feed),
 https://orcid.org/0000-0001-6183-7603
2016:
Zoltán Szabó, Bharath K. Sriperumbudur, Barnabás Póczos, Arthur Gretton. Learning Theory for Distribution Regression. Journal of Machine Learning Research, 2016. [accepted; arXiv: abstract, paper; code]
Wittawat Jitkrittum, Zoltán Szabó, Kacper Chwialkowski, Arthur Gretton. Interpretable Distribution Features with Maximum Testing Power. In Neural Information Processing Systems (NIPS-2016), Barcelona, Spain, 5-10 December 2016. [full oral presentation - 1.84% acceptance rate; arXiv: abstract, paper; code]
Heiko Strathmann, Dino Sejdinovic, Samuel Livingston, Ingmar Schuster, Maria Lomeli Garcia, Zoltán Szabó, Christophe Andrieu, Arthur Gretton. Kernel techniques for adaptive Monte Carlo methods. In Greek Stochastics Workshop on Big Data and Big Models, Tinos, Greek, 10-13 July 2016. [slides]
Wittawat Jitkrittum, Zoltán Szabó, Kacper Chwialkowski, Arthur Gretton. Distinguishing Distributions with Interpretable Features. In International Conference on Machine Learning (ICML):Data-Efficient Machine Learning workshop, New York, U.S., 24 June 2016. [paper, spotlight, poster, code]
Zoltán Szabó, Bharath K. Sriperumbudur, Barnabás Póczos, Arthur Gretton. Minimax-optimal distribution regression. In International Society for NonParametric Statistics (ISNPS) Conference, Avignon, France, 11-16 June 2016. [abstract, slides, code]
Bharath K. Sriperumbudur, Zoltán Szabó (contributed equally). Optimal Uniform and Lp Rates for Random Fourier Features. In Theory of Big Data Workshop, London, UK, 6-8 January 2016. [abstract, poster]
2015:
Bharath K. Sriperumbudur, Zoltán Szabó (contributed equally). Optimal Rates for Random Fourier Features. In Neural Information Processing Systems (NIPS-2015), pages 1144-1152, Montréal, Canada, 7-12 December 2015. [spotlight presentation - 3.65% acceptance rate; spotlight, poster, paper; paper (NIPS website); arXiv: abstract, paper]
Heiko Strathmann, Dino Sejdinovic, Samuel Livingston, Zoltán Szabó, Arthur Gretton. Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families. In Neural Information Processing Systems (NIPS-2015), pages 955-963, Montréal, Canada, 7-12 December 2015. [poster presentation - 17.46% acceptance rate; poster, paper, code; paper (NIPS website); arXiv: abstract, paper]
Mijung Park, Wittawat Jitkrittum, Ahmad Qamar, Zoltán Szabó, Lars Buesing, Maneesh Sahani. Bayesian Manifold Learning: The Locally Linear Latent Variable Model. In Neural Information Processing Systems (NIPS-2015), pages 154-162, Montréal, Canada, 7-12 December 2015. [poster presentation - 17.46% acceptance rate; poster, paper, code; paper (NIPS website); arXiv: abstract, paper]
Wittawat Jitkrittum, Arthur Gretton, Nicolas Heess, S. M. Ali Eslami, Balaji Lakshminarayanan, Dino Sejdinovic, Zoltán Szabó. Just-In-Time Kernel Regression for Expectation Propagation. In International Conference on Machine Learning (ICML) - Large-Scale Kernel Learning: Challenges and New Opportunities workshop, Lille, France, 10-11 July 2015. [paper, poster, code]
Wittawat Jitkrittum, Arthur Gretton, Nicolas Heess, S. M. Ali Eslami, Balaji Lakshminarayanan, Dino Sejdinovic, Zoltán Szabó. Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages. In Conference on Uncertainty in Artificial Intelligence (UAI-2015), pages 405-414, Amsterdam, Netherlands, 12-16 July 2015. [paper (=UAI: main + supplement), spotlight, poster, code; arXiv: abstract, paper]
Zoltán Szabó, Bharath K. Sriperumbudur, Barnabás Póczos, Arthur Gretton. Distribution Regression - Make It Simple and Consistent. In Data, Learning and Inference workshop (DALI), La Palma (Canaries, Spain), 10-12 April 2015. [poster; arXiv: abstract, paper; code]
Wittawat Jitkrittum, Arthur Gretton, Nicolas Heess, S. M. Ali Eslami, Balaji Lakshminarayanan, Dino Sejdinovic, Zoltán Szabó. Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages. In Data, Learning and Inference workshop (DALI), La Palma (Canaries, Spain), 10-12 April 2015. [poster, code]
Zoltán Szabó, Arthur Gretton, Barnabás Póczos, Bharath K. Sriperumbudur. Two-stage Sampled Learning Theory on Distributions. In International Conference on Artificial Intelligence and Statistics (AISTATS), pages 948-957, San Diego, California, USA, 9-12 May 2015. [oral presentation, 6.11% oral acceptance rate; slides, paper, code; arXiv: abstract, paper]
Zoltán Szabó, Arthur Gretton, Barnabás Póczos, Bharath K. Sriperumbudur. Consistent Vector-valued Distribution Regression. In UCL Workshop on the Theory of Big Data, London, UK, 7-9 January 2015. [abstract, slides, code]
Balázs Pintér, Gyula Vörös, Zoltán Szabó, and András Lőrincz. Wikifying novel words to mixtures of Wikipedia senses by structured sparse coding. In Pattern Recognition Applications and Methods, volume 318 of Advances in Intelligent and Soft Computing, pages 241-255. Springer, 2015. [paper, DOI]
2014:
Zoltán Szabó, Arthur Gretton, Barnabás Póczos, Bharath K. Sriperumbudur. Simple Consistent Distribution Regression on Compact Metric Domains. In UCL-Duke Workshop on Sensing and Analysis of High-Dimensional Data (SAHD), London, UK, 4-5 September 2014. [abstract, poster, code]
Zoltán Szabó, Arthur Gretton, Barnabás Póczos, Bharath K. Sriperumbudur. Learning on Distributions. Kernel methods for big data workshop, Lille, France, 2 April 2014. [abstract, slides, paper, code]
Zoltán Szabó. Information Theoretical Estimators Toolbox. Journal of Machine Learning Research 15:283-287, 2014. [abstract, paper; arXiv: paper; ITE toolbox]
László Jeni, András Lőrincz, Zoltán Szabó, Jeffrey Cohn, and Takeo Kanade. Spatio-temporal event classification using time-series kernel based structured sparsity. In European Conference on Computer Vision (ECCV), volume 8692 of LNCS - Part IV., pages 135-150, Zürich, Switzerland, 6-12 September 2014. [paper, supplementary material, video demo, poster, DOI]
2013:
Zoltán Szabó. Information Theoretical Estimators (ITE) Toolbox. In Neural Information Processing Systems (NIPS) - Workshop on Machine Learning Open Source Software 2013: Towards Open Workflows, Lake Tahoe, Nevada, United States, 10 December 2013. [abstract, highlight slide, ITE toolbox]
András Lőrincz, László A. Jeni, Zoltán Szabó, Jeffrey Cohn, and Takeo Kanade. Emotional expression classification using time-series kernels. In IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG), pages 889-895, Portland, Oregon, 23-28 June 2013. [paper; arXiv: paper, DOI]
Balázs Pintér, Gyula Vörös, Zoltán Szabó, and András Lőrincz. Explaining unintelligible words by means of their context. In International Conference on Pattern Recognition Applications and Methods (ICPRAM), pages 382-387, Barcelona, Spain, 15-18 February 2013. [paper]
Balázs Pintér, Gyula Vörös, Zsolt Palotai, Zoltán Szabó, and András Lőrincz. Determining unintelligible words from their textual contexts. Procedia - Social and Behavioral Sciences, 73:101-108, 2013. (Proceedings of International Conference on Integrated Information (IC-ININFO), Budapest, Hungary, 30 August - 3 September 2012). [paper, DOI, slides]
2012:
Balázs Pintér, Gyula Vörös, Zoltán Szabó, and András Lőrincz. Automated Word Puzzle Generation via Topic Dictionaries. In International Conference on Machine Learning (ICML) - Sparsity, Dictionaries and Projections in Machine Learning and Signal Processing Workshop, Edinburgh, Scotland, 30 June 2012. [paper, slides; arXiv: paper]
Zoltán Szabó. Group-Structured and Independent Subspace Based Dictionary Learning. PhD thesis, Eötvös Loránd University, Budapest, 2012. [paper]
Zoltán Szabó and András Lőrincz. Distributed High Dimensional Information Theoretical Image Registration via Random Projections. Digital Signal Processing, 22(6):894-902, 2012. [paper, DOI; arXiv: abstract].
Balázs Pintér, Gyula Vörös, Zoltán Szabó, and András Lőrincz. Automated Word Puzzle Generation Using Topic Models and Semantic Relatedness Measures. Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös Nominatae, Sectio Computatorica, 36: 299-322, 2012. (journal version of our MACS paper) [paper]
László A. Jeni, András Lőrincz, Tamás Nagy, Zsolt Palotai, Judit Sebők, Zoltán Szabó, and Dániel Takács. 3D Shape Estimation in Video Sequences Provides High Precision Evaluation of Facial Expressions. Image and Vision Computing, 30(10):785–795, 2012. [paper, DOI]
Balázs Pintér, Gyula Vörös, Zoltán Szabó, and András Lőrincz. Automated Word Puzzle Generation Using Topic Models and Semantic Relatedness Measures. In Joint Conference on Mathematics and Computer Science (MaCS), 2012. [paper, slides]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Collaborative Filtering via Group-Structured Dictionary Learning. In International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA), volume 7191 of LNCS, pages 247-254, Tel-Aviv, Israel, 12-15 March 2012. Springer-Verlag, Berlin Heidelberg. [paper = compressed version of the paper on arXiv: abstract; poster spotlight, poster, DOI]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Separation Theorem for Independent Subspace Analysis and its Consequences. Pattern Recognition, 45:1782-1791, 2012. [paper, DOI, code]
2011:
András Lőrincz, Viktor Gyenes, Zsolt Palotai, Balázs Pintér, Zoltán Szabó, Gyula Vörös: Innovation Engine in Blogspace. Technical Report, EOARD - US Air Force Research Laboratories, 2011. [paper]
Barnabás Póczos, Zoltán Szabó, and Jeff Schneider. Nonparametric divergence estimators for Independent Subspace Analysis. In European Signal Processing Conference (EUSIPCO) - Special Session on Dependent Component Analysis, pages 1849-1853, Barcelona, Spain, 29 August - 2 September 2011. [paper, slides]
Zoltán Szabó and Barnabás Póczos. Nonparametric Independent Process Analysis. In European Signal Processing Conference (EUSIPCO), pages 1718-1722, Barcelona, Spain, 29 August - 2 September 2011. [paper, poster]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz: Online Dictionary Learning with Group Structure Inducing Norms. In International Conference on Machine Learning (ICML) - Structured Sparsity: Learning and Inference Workshop, Bellevue, Washington, USA, 2 July 2011. [paper = workshop's paper, slides, poster]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz: Online Group-Structured Dictionary Learning. In IEEE Computer Vision and Pattern Recognition (CVPR), pages 2865-2872, Colorado Springs, CO, USA, 20-25 June 2011. [paper, supplementary material, paper+supplementary material, poster, DOI, code]
2010:
Zoltán Szabó: Towards Nonstationary, Nonparametric Independent Process Analysis with Unknown Source Component Dimensions. Technical report, Eötvös Loránd University, Budapest, 2010. [arXiv: abstract]
Zoltán Szabó. Autoregressive Independent Process Analysis with Missing Observations. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Bruges, Belgium. d-side (2010), pages 159-164. [paper, poster spotlight, poster]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Auto-Regressive Independent Process Analysis without Combinatorial Efforts. Pattern Analysis and Applications, 13:1-13, 2010. [paper, DOI]
2009:
Zoltán Szabó. Independent Subspace Analysis in Case of Missing Observations. In Symposium of Intelligent Systems, 2009. [poster (in Hungarian)]
Zoltán Szabó and András Lőrincz. Complex Independent Process Analysis. Acta Cybernetica 19:177-190, 2009. [paper, paper (AC)]
Zoltán Szabó. Separation Principles in Independent Process Analysis. PhD thesis, Eötvös Loránd University, Budapest, 2009. [paper]
Zoltán Szabó and András Lőrincz. Controlled Complete ARMA Independent Process Analysis. In International Joint Conference on Neural Networks (IJCNN), pages 3038-3045, Atlanta, Georgia, USA, 14-19 June 2009. [paper, DOI]
Zoltán Szabó and András Lőrincz. Fast Parallel Estimation of High Dimensional Information Theoretical Quantities with Low Dimensional Random Projection Ensembles. In International Conference on Independent Component Analysis and Signal Separation (ICA), volume 5441 of LNCS, pages 146-153, Paraty, Brazil, 15-18 March 2009. Springer-Verlag Berlin Heidelberg. [paper, poster, DOI]
Zoltán Szabó. Complete Blind Subspace Deconvolution. In International Conference on Independent Component Analysis and Signal Separation (ICA), volume 5441 of LNCS, pages 138-145, Paraty, Brazil, 15-18 March 2009. Springer-Verlag Berlin Heidelberg. [paper, poster, DOI]
2008:
Zoltán Szabó and András Lőrincz. Towards Independent Subspace Analysis in Controlled Dynamical Systems. In ICA Research Network International Workshop (ICARN), pages 9-12, Liverpool, U.K., 2008. [paper, slides]
Zoltán Szabó, and András Lőrincz. Post Nonlinear Hidden Infomax Identification. In Joint Conference of Hungarian PhD students, pages 52-58, Budapest, Hungary, 23-25 May 2008. [paper (in Hungarian), slides (in Hungarian)]
2007:
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Undercomplete Blind Subspace Deconvolution via Linear Prediction. In European Conference on Machine Learning (ECML) volume 4701 of LNAI, pages 740-747, Warsaw, Poland, 17-21 September 2007. Springer-Verlag. [paper, arXiv: abstract; poster highlight, poster, DOI]
Zoltán Szabó, Barnabás Póczos, Gábor Szirtes, and András Lőrincz. Post Nonlinear Independent Subspace Analysis. In International Conference on Artificial Neural Networks (ICANN) volume 4668 of LNCS - Part I., pages 677-686, Porto, Portugal, 9-13 September 2007. Springer-Verlag. [paper, slides, DOI]
Barnabás Póczos, Zoltán Szabó, Melinda Kiszlinger, and András Lőrincz. Independent Process Analysis without A Priori Dimensional Information. In International Conference on Independent Component Analysis and Signal Separation (ICA) volume 4666 of LNCS, pages 252-259, London, U.K., 9-12 September 2007. Springer-Verlag, Berlin Heidelberg. [paper, arXiv: abstract; DOI]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Undercomplete Blind Subspace Deconvolution. Journal of Machine Learning Research 8(May):1063-1095, 2007. [paper, arXiv: abstract]
András Lőrincz and Zoltán Szabó. Neurally Plausible, Non-combinatorial Iterative Independent Process Analysis. Neurocomputing - Letters 70(7-9):1569-1573, 2007. [paper, DOI]
Zoltán Szabó and András Lőrincz. Independent Subspace Analysis can Cope with the ,,Curse of Dimensionality''. Acta Cybernetica 18:213-221, 2007. (Symposium of Intelligent Systems, 2006). [paper, poster (in Hungarian)]
Zoltán Szabó and András Lőrincz. Multilayer Kerceptron. Journal of Applied Mathematics 24:209-222, 2007. [paper (in English), paper (in Hungarian)]
2006:
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Separation Theorem for K-Independent Subspace Analysis with Sufficient Conditions. Technical report, Eötvös Loránd University, Budapest, 2006. [arXiv: abstract]
Zoltán Szabó and András Lőrincz. Real and Complex Independent Subspace Analysis by Generalized Variance. In ICA Research Network International Workshop (ICARN), pages 85-88, Liverpool, U.K., 18-19 September 2006. [paper, arXiv: abstract; slides]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Cross-Entropy Optimization for Independent Process Analysis. In International Conference on Independent Component Analysis and Blind Source Separation (ICA) volume 3889 of LNCS, pages 909-916, Charleston, SC, USA, 5-8 March 2006. Springer. [paper, poster, DOI]
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Separation Theorem for Independent Subspace Analysis with Sufficient Conditions. Technical report, Eötvös Loránd University, Budapest, 2006. [arXiv: abstract]
Zoltán Szabó and András Lőrincz. Epsilon-Sparse Representations: Generalized Sparse Approximation and the Equivalent Family of SVM Tasks. Acta Cybernetica 17(3):605-614, 2006. [paper]
2005:
Zoltán Szabó, Barnabás Póczos, and András Lőrincz. Separation Theorem for Independent Subspace Analysis. Technical report, Eötvös Loránd University, Budapest, 2005. [paper]
2004:
Zoltán Szabó and András Lőrincz. L1 regularization is better than L2 for learning and predicting chaotic systems. Technical report, Eötvös Loránd University, Budapest, 2004. [arXiv: paper]
György Hévízi, Mihály Biczó, Barnabás Póczos, Zoltán Szabó, Bálint Takács, and András Lőrincz. Hidden Markov Model Finds Behavioral Patterns of Users Working with a Headmouse Driven Writing Tool. In International Joint Conference of Neural Networks (IJCNN), Budapest, Hungary, 26-29 July, 2004. [paper, slides, DOI]
2003:
Zoltán Szabó. Retina based sampling in face component recognition. Master's thesis, Eötvös Loránd University, Budapest, 2003. [title page, acknowledgements, abstract (in Hungarian)]

HTML5 | CSS3