BALÁZS CsANÁD CsÁJI

[ Positions ]   [ Degrees ]   [ Interests ]   [ Visits ]   [ Teaching ]   [ Projects ]   [ Awards ]   [ Memberships ]   [ Publications ]   [ Languages ]   [ Students ]

 CURRENT POSITIONS

Balázs  Csanád  Csáji

Senior Researcher
Engineering and Management Intelligence Laboratory
Institute for Computer Science and Control (SZTAKI)
Hungarian Research Network (HUN-REN)

Room K615, Central Building
13-17 Kende utca, XI. kerület
Budapest, Hungary, H 1111

Phone: (+36) 1-279-6231
csaji [at] sztaki [dot] hu


Adjunct Professor
Department of Probability Theory and Statistics
Institute of Mathematics, Faculty of Science
Eötvös Loránd University (ELTE)

Room 3.413, South Building
1/C Pázmány Péter sétány
Budapest, Hungary, H 1117

Phone: (+36) 1-381-2202
csaji.balazs [at] ttk [dot] elte [dot] hu

 EDUCATION AND DEGREES

    Ph.D. in Computer Science, Faculty of Informatics, Eötvös Loránd University (ELTE-IK), Budapest, Hungary, 2008
Thesis: Adaptive Resource Control: Machine Learning Approaches to Resource Allocation in Uncertain and Changing Environments
Supervisor: László Monostori, Budapest University of Technology and Economics (BME), Budapest, Hungary
    M.A. in Philosophy, Faculty of Humanities, Eötvös Loránd University (ELTE-BTK), Budapest, Hungary, 2006
Thesis: Paradoxes in Rational Collective Decisions (Philosophy of Science & Social Philosophy)
Supervisor: Miklós Rédei, London School of Economics and Political Science (LSE), London, United Kingdom
    M.Sc. in Mathematics & Computer Science*, Faculty of Science, Eötvös Loránd University (ELTE-TTK), Budapest, Hungary, 2001
Thesis: Approximation with Artificial Neural Networks (Machine Learning & Wavelet Analysis)
Supervisor: Huub ten Eikelder, Eindhoven University of Technology (TU/e), Eindhoven, Netherlands
* In Hungarian: "programtervező matematikus" (verbatim: "program-designer mathematician")

 FIELDS OF INTEREST

    Computer Science Machine Learning (Statistical and Reinforcement Learning); Resource Allocation; Randomized Algorithms
    Applied Mathematics Statistical Inference (Non-Parametric); Probabilistic Models; Stochastic Approximation; Operations Research
    Control Engineering System Identification (Non-Asymptotic); Stochastic-, Robust- and Adaptive Control; Model Predictive Control
    Analytic Philosophy Philosophy of Science (Problem of Induction); Interpretations of Probability; Foundations of Mathematics; Logic

 RESEARCH VISITS

    Long-term Visits
        2009 – 2012 Department of Electrical and Electronic Engineering, University of Melbourne, ARC Research Fellow, 3 years, Australia
        2008 – 2009 Department of Mathematical Engineering, Université catholique de Louvain, Research Fellow, 8 months, Belgium
        2003 Institute for Applied Knowledge Processing, Johannes Kepler University, CEEPUS Scholarship, 4 months, Austria
        2002 Radical Multimedia Lab, BTexact Technologies, British Telecom, IAESTE Exchange Program, 3 months, United Kingdom
        2001 Faculty of Mathematics and Computing Science, Technical University of Eindhoven, ERASMUS, 5 months, Netherlands
    Short-term Visits
        2012 Department of Information Engineering, University of Brescia, Italy
        2012 Faculty of Electrical Engineering, Computer Science, and Mathematics, University of Paderborn, Germany
        2009 Department of Electrical Engineering and Computer Science, University of Liège, Belgium
        2009 Robot Learning Group, Dalle Molle Institute for Artificial Intelligence (IDSIA), University of Lugano, Switzerland
        2008 Institute of Perception, Action and Behaviour, School of Informatics, University of Edinburgh, United Kingdom
        2008 Gatsby Computational and Theoretical Neuroscience and Machine Learning Unit, University College London, United Kingdom
        2008 Alberta Ingenuity Center for Machine Learning, Department of Computing Science, University of Alberta, Canada

 TEACHING AND LECTURES

    Teaching Activity
        2024 – Data Mining and Machine Learning, Lectures for B.Sc. Students in Mathematics, Major Block: Modelling, Department of Probability Theory and Statistics, Institute of Mathematics, Eötvös Loránd University (ELTE), Budapest, Hungary
        2023 – Statistical Learning and Kernel Methods, Lectures for M.Sc. and Ph.D. Students in Applied and Pure Mathematics, Department of Probability Theory and Statistics, Institute of Mathematics, Eötvös Loránd University (ELTE), Budapest, Hungary
        2022 – Mathematical Statistics, Lectures and Seminars for B.Sc. Students in Applied and Pure Mathematics, Department of Probability Theory and Statistics, Institute of Mathematics, Eötvös Loránd University (ELTE), Budapest, Hungary
        2021 – Probability Theory II, Seminars for B.Sc. Students in Appl. Mathematics, Eötvös Loránd University (ELTE), Budapest, Hungary
        2019 – Markov Decision Processes and Reinforcement Learning (MDPs & RL), Lectures for M.Sc. and Ph.D. Students in Mathematics, Institute of Mathematics, Budapest University of Technology and Economics (BME), Hungary; and (from 2022) Department of Probability Theory and Statistics, Institute of Mathematics, Eötvös Loránd University (ELTE), Budapest, Hungary [slides]
        2019 – 2022 Mathematical Foundations of Machine Learning (MFML), Lectures for M.Sc. and Ph.D. Students in Applied Mathematics, Institute of Mathematics, Eötvös Loránd University (ELTE), Budapest, Hungary [syllabus] [slides]
        2015 – 2021 Stochastic Models and Adaptive Algorithms, Ph.D. School of Computer Science, Eötvös Loránd University (ELTE), Budapest, Hungary, and (since 2017) Budapest University of Technology and Economics (BME), Budapest, Hungary [slides]
        2013 – 2014 Mathematical Optimization (main organizer), SZTAKI: Institute for Computer Science and Control, Budapest, Hungary
        2012 Probability and Random Models (ELEN90054, with Girish Nair), School of Engineering, University of Melbourne, Australia
        2005 – 2006 Markov Decision Processes (organized by Cs. Szepesvári), SZTAKI: Institute for Computer Science and Control, Hungary
        2002 Theory of Operating Systems, Department of Information Systems, Eötvös Loránd University (ELTE), Budapest, Hungary
        2000 – 2002 Programming Methodology, Department of Software Technology, Eötvös Loránd University (ELTE), Budapest, Hungary
    Lecture Slides
        2023 The Huge Potential of AI in CAR-T Cell Therapies, Artificial Intelligence and Automation Expo, Budapest, Hungary [slides]
        2021 Uncertainty Quantification and Kernels: Distribution-Free Inference for Regression and Classification; Deep Learning Seminar, Artificial Intelligence National Laboratory, Alfréd Rényi Institute of Mathematics, Budapest, Hungary [slides]
        2021 Stochastic Optimization in Machine Learning: Inhomogeneity, Quantization and Acceleration; Data Analysis and Optimization Seminar, Budapest University of Technology and Economics (BME), Budapest, Hungary [slides]
        2017 On the Reliability of Regression Models, Publication Award Seminar, SZTAKI, Budapest, Hungary [slides]
        2012 Distribution-Free System Identification: Exact-, Non-Asymptotic Confidence Regions, Faculty of Electrical Engineering, Computer Science, and Mathematics, University of Paderborn, Germany [slides]
        2010 Introduction to Markov Decision Processes, Department of Electrical Engineering, University of Melbourne, Australia [slides]
        2009 A Machine Learning Approach to Stochastic Resource Control, Poster, DYSCO Study Day, Mons, Belgium [poster]
        2008 Learning in Changing Environments: Reinforcement Learning in Environments with Asymptotically Bounded Variation, Gatsby Computational and Theoretical Neuroscience and Machine Learning Unit, University College London (UCL), UK [slides]
        2006 Introduction to Off-Policy Learning, MDP Seminar, SZTAKI, Budapest, Hungary [slides]
        2005 Introduction to Temporal Difference Learning (Hungarian Slides), MDP Seminar, SZTAKI, Budapest, Hungary [slides]
        2004 Intuitionism in Mathematics (Philosophy of Mathematics), HalSzem, ELTE, Budapest, Hungary [pdf] Handout [pdf]

 RESEARCH PROJECTS

    European Projects
        2020 – Arificial Intelligence National Laboratory (Task: Mathematical Foundations of AI), RRF-2.3.1-21-2022-00004, EU
        2020 – Autonomous Systems National Laboratory (Task: Identification and Control), RRF-2.3.1-21-2022-00002, EU
        2021 – 2024 AIDPATH: Artificial Intelligence-driven, Decentralized Production for Advanced Therapies in the Hospital, EU H2020
        2018 – 2019 BioManu-II: Biologicalisation in Manufacturing, Fraunhofer-Gesellschaft, Germany
        2005 – 2009 Coll-Plexity: Collaborations as Complex Systems (Project Manager for SZTAKI), Nest Program, 6th Framework, EU
        2004 – 2006 MultiSens: Cameras as Multifunctional Sensors for Automated Processes, 6th Framework, EU
        2000 – 2004 MPA: Modular Plant Architecture, Growth Project, 5th Framework, EU
    National Projects
        2022 – COPROLOGS: Cooperative Production and Logistics Systems to Support a Competitive and Sustainable Economy (Task A1.2: Predictive Methods), TKP2021-NKTA-01, National Programme for Research and Innovation (NKFIH), Hungary
        2018 – 2023 INEXT: Research on the Prime Exploitation of the Potential Provided by Industrial Digitalisation (Task A.3: Machine Learning in Stochastic Dynamic Systems), National Programme for Research and Innovation (NKFIH), Hungary
        2018 – 2021 Exloring the Mathematical Foundations of Artificial Intelligence, National Excellence Program (NKP), Hungary
        2017 – 2019 Markov Decision Processes: Estimation and Approximation Methods (Principal Investigator), KH_17, NKFIH, Hungary
        2014 – 2016 Analytical Module for a Wireless Multi-Sensor Network (Principal Investigator), comissioned by GE Lighting, Hungary
        2011 – 2014 E+Grid: An Embedded System for Optimizing Energy Positive Public Lighting Service, National Development Agency, Hungary
        2008 – 2010 Production Structures as Complex Adaptive Systems, Hungarian Scientific Research Fund (OTKA), Hungary
        2004 – 2007 VITAL: Real-Time, Cooperative Enterprises, National Programme for Research and Innovation (NKFP), Hungary
        2005 – 2007 Modeling, Planning and Control of Distributed, Modular Production Structures, Hungarian Scientific Research Fund (OTKA)
    University Projects
        2011 – 2012 Distribution-Free System Identification (Principal Investigator), Australian Research Council (ARC), Australia
        2009 – 2011 Algorithms for Change Detection Based on Finite Sample System Identification, Australian Research Council (ARC), Australia
        2009 Data Mining in Mobile Networks, Department of Mathematical Engineering, Catholic University of Louvain, Belgium
        2003 Learning and Maintaining Similarity Information in Flexible Query Answering Systems, Johannes Kepler University, Austria
        2002 Physics Engine for the TARA Graphical Library, Radical Multimedia Lab, British Telecom, United Kingdom
        2001 Constructive Approximation with Feed-forward Artificial Neural Networks, Technical University of Eindhoven, Netherlands
        2000 Augmented Reality for Parkinson Patients, Eötvös Loránd University (ELTE) and Semmelweis University, Hungary

 AWARDS AND SCHOLARSHIPS

    Honors and Awards
        2022 Best Ph.D. Supervisor Award, SZTAKI: Institute for Computer Science and Control
        2020 Bolyai Certificate of Merit (for the results of the 2nd Bolyai Fellowship), Hungarian Academy of Sciences (MTA)
        2019 Plenary Speaker, 33rd Hungarian Conference on Operations Research (MOK), May 20-22, Szeged (Hungary)
        2016 Béla Gyires Prize (Applied Mathematics), Section of Mathematics, Hungarian Academy of Sciences (MTA)
        2016 Bolyai Certificate of Merit (for the results of the 1st Bolyai Fellowship), Hungarian Academy of Sciences (MTA)
        2013 Outstanding Reviewer, IEEE Transactions on Automatic Control (TAC), IEEE Control Systems Society (CSS)
        2011 Discovery Early Career Researcher Award (DECRA, Applied Mathematics), Australian Research Council (ARC)
        2009 Finalist (top 5) of the Cor Baayen Award, European Research Consortium for Informatics and Mathematics (ERCIM)
        2009 Young Researchers' Award (Mathematical Sciences), Hungarian Academy of Sciences (MTA)
        2009, 16, 18 Publication Award (3x), SZTAKI: Institute for Computer Science and Control
        2006 Young Researchers' Institute Award, SZTAKI: Institute for Computer Science and Control
        2006 Best Paper Award, 6th International Workshop on Emergent Synthesis (IWES), University of Tokyo (Japan)
        2004 Best Ph.D. Student Award, SZTAKI: Institute for Computer Science and Control
        2004, 09, 15 Institute Award (3x), SZTAKI: Institute for Computer Science and Control
        2000 First Prize, Section of Informatics, Scientific Student Conference (TDK), Eötvös Loránd University (ELTE)
    Grants and Scholarships
        2020 – 2024 Supervisor, Cooperative Doctoral Programme (Tamás, A.), National Programme for Research and Innovation (NKFIH)
        2016 – 2019 János Bolyai Research Fellowship (2nd term), Hungarian Academy of Sciences (MTA)
        2012 – 2015 János Bolyai Research Fellowship (1st term), Hungarian Academy of Sciences (MTA)
        2011 – 2013 ARC DECRA Fellowship, Australian Research Council (ARC)
        2004 – 2007 Young Researcher Scholarship, Hungarian Academy of Sciences (MTA)
        2001 – 2004 Ph.D. Scholarship, Eötvös Loránd University (ELTE)
        2000 – 2001 Research Scholarship (Artificial Intelligence), Pázmány-Eötvös Foundation

 PROFESSIONAL MEMBERSHIPS

        2023 – Section of Mathematics (member of public body), Hungarian Academy of Sciences (MTA)
         – Scientific Committee: Operations Research (voting right)
        2019 – János Bolyai Mathematical Society (BJMT)
         Vice Chair: Section of Applied Mathematics
        2015 – Hungarian Operations Research Society (MOT)
        2014 – International Federation of Automatic Control (IFAC)
         – Technical Committee (1.1): Modelling, Identification and Signal Processing
         – Technical Committee (1.2): Adaptive and Learning Systems
         – Technical Committee (5.4): Large Scale Complex Systems
        2013 – Institute of Electrical and Electronic Engineers (IEEE), Control Systems Society (CSS)
         – Technical Committee: System Identification and Adaptive Control

 BIBLIOMETRICS

        All publications: 90+ Independent citations*: 2000+ Cumulative impact factor: 56+ Erdős number**: 3
        Journal articles: 32 Book chapters & LNCS/AI: 8 Conference & workshop papers: 50 Invited talks: 20+
        * A [citation] is independent if none of the authors of the citing paper is an author of the cited paper ** [proof]

 SELECTED PUBLICATIONS

    Drafts and Preprints
        – Tamás, A.; Csáji, B. Cs.: Recursive Estimation of Conditional Kernel Mean Embeddings [arxiv]
        – Tamás, A.; Csáji, B. Cs.: Distribution-Free Inference for the Regression Function of Binary Classification [arxiv]
        – Carè, A.; Csáji, B. Cs.; Gerencsér, B.; Gerencsér, L.; Rásonyi, M.: Poisson Equations, Lipschitz Continuity and Controlled Queues [arxiv]
        – Carè, A.; Weyer, E.; Csáji, B. Cs.; Campi, M.: Signed-Perturbed Sums Estimation of ARX Systems: Exact Coverage and Strong Consistency [arxiv]
        – Csáji, B. Cs.; Györfi, L.; Tamás, A.; Walk, H.: On Rate-Optimal Partitioning Classification from Observable and from Privatised Data [arxiv]
    Selected Journal Papers
        – Tamás, A.; Bálint, D. Á.; Csáji, B. Cs.: Robust Independence Tests with Finite Sample Guarantees for Synchronous Stochastic Linear Systems, IEEE Control Systems Letters (L-CSS), IEEE Press, Vol. 7, 2023, pp. 2701–2706 [arxiv]
        – Szentpéteri Sz.; Csáji, B. Cs.: Non-Asymptotic State-Space Identification of Closed-Loop Stochastic Linear Systems using Instrumental Variables, Systems & Control Letters, Elsevier, Vol. 178, August 2023, 105565 [arxiv] [link]
        – Csáji, B. Cs.; Horváth, B.: Nonparametric, Nonasymptotic Confidence Bands with Paley-Wiener Kernels for Band-Limited Functions, IEEE Control Systems Letters (L-CSS), IEEE Press, Vol. 6, 2022, pp. 3355–3360 [arxiv]
        – Tamás, A.; Csáji, B. Cs.: Exact Distribution-Free Hypothesis Tests for the Regression Function of Binary Classification via Conditional Kernel Mean Embeddings, IEEE Control Systems Letters (L-CSS), IEEE Press, Vol. 6, 2022, pp. 860–865 [arxiv]
        – Carè, A.; Campi, M. C.; Csáji, B. Cs.; Weyer, E.: Facing Undermodelling in Sign-Perturbed Sums System Identification, Systems & Control Letters, Elsevier, Vol. 153, July 2021, 104936 [pdf]
        – Monostori, L.; Csáji, B. Cs.; Egri, P.; Kis, K. B.; Váncza, J.; Ochs, J.; Jung, S.; König, N.; Pieske, S.; Wein, S.; Schmitt, R.; Brecher, C.: Automated Stem Cell Production by Bio-Inspired Control, CIRP Journal of Manufacturing Science and Technology, Elsevier, Vol. 33, 2021, 369–379 [pdf]
        – Csáji, B. Cs.; Kis, K. B.: Distribution-Free Uncertainty Quantification for Kernel Methods by Gradient Perturbations, Machine Learning, Springer, Special Issue of the European Conference on Machine Learning (ECML PKDD Journal Track), Vol. 108, 2019, pp. 1677–1699 [arxiv] [link]
        – Weyer, E.; Campi, M. C.; Csáji, B. Cs.: Asymptotic Properties of SPS Confidence Regions, Automatica, Elsevier, Vol. 82, 2017, pp. 287–294 [pdf]
        – Csáji, B. Cs.; Kemény, Zs.; Pedone, G.; Kuti, A.; Váncza, J.: Wireless Multi-Sensor Networks for Smart Cities: A Prototype System with Statistical Data Analysis, IEEE Sensors Journal, IEEE Press, Vol. 17, Issue 23, 2017, pp. 7667–7676 [arxiv]
        – Carè, A.; Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Finite-Sample System Identification: An Overview and a New Correlation Method, IEEE Control Systems Letters (L-CSS), IEEE Press, Vol. 2, No. 1, 2017, pp. 61–66 [pdf]
        – Kovács, A.; Bátai, R.; Csáji, B. Cs.; Dudás, P.; Háy, B.; Pedone, G.; Révész, T.; Váncza, J.: Intelligent Control for Energy-Positive Street Lighting, Energy: The International Journal, Elsevier, Vol. 114, 2016, pp. 40–51 [pdf]
        – Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Sign-Perturbed Sums: A New System Identification Approach for Constructing Exact Non-Asymptotic Confidence Regions in Linear Regression Models, IEEE Transactions on Signal Processing, IEEE Press, Vol. 69, 2015, pp. 169–181 [pdf]
        – Monostori, L.; Valckenaers, P.; Dolgui, A.; Panetto, H.; Brdys, M.; Csáji, B. Cs.: Cooperative Control in Production and Logistics, Annual Reviews in Control (ARC): A Journal of IFAC, the International Federation of Automatic Control, Elsevier, Vol. 39, 2015, pp. 12–29 [pdf]
        – Csáji, B. Cs.; Jungers, R. M.; Blondel, V. D.: PageRank Optimization by Edge Selection, Discrete Applied Mathematics (DAM): The Journal of Combinatorial Algorithms, Informatics and Computational Sciences, Elsevier, Vol. 169, 2014, pp. 73–87 [pdf]
        – Csáji, B. Cs.; Browet, A.; Traag, V. A.; Delvenne, J-C.; Huens, E.; Van Dooren, P.; Smoreda, Z.; Blondel, V. D.: Exploring the Mobility of Mobile Phone Users, Physica A: Statistical Mechanics and its Applications, Elsevier, Vol. 392, Issue 6, 2013, pp. 1459–1473 [pdf]
        – Csáji, B. Cs.; Monostori, L.: Adaptive Stochastic Resource Control: A Machine Learning Approach, Journal of Artificial Intelligence Research (JAIR), AAAI Press, Vol. 32, 2008, pp. 453–486 [pdf]
        – Csáji, B. Cs.; Monostori, L.: Value Function Based Reinforcement Learning in Changing Markovian Environments, Journal of Machine Learning Research (JMLR), MIT Press and Microtome Publishing, Vol. 9, 2008, pp. 1679–1709 [pdf]
    Selected Conference Papers
        – Tamás, A.; Szentpéteri, Sz.; Csáji, B. Cs.: Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions, 27th International Conference on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, May 2–4, 2024, PMLR: Vol. 238 [pdf] [poster]
        – Szentpéteri, Sz.; Kis, K. B; Egri, P.; Sanges, C.; Danhof, S.; Mestermann, K.; Hudecek, M.; Navarro Velázquez, S.; Juan, M.; Csáji, B. Cs.: Reinforcement Learning Based Resource Management for CAR T-Cell Therapies, 6th CIRP Conference on Biomanufacturing (BioM), Dresden, Germany, June 11–13, 2024 [pdf]
        – Horváth, B.; Csáji, B. Cs.: Nonparametric Simultaneous Confidence Bands: The Case of Known Input Distributions, 23rd European Young Statisticians Meeting (EYSM 2023, virtual mode), Ljubljana, Slovenia, September 11–15, 2023 [pdf]
        – Szentpéteri, Sz.; Csáji, B. Cs.: Sample Complexity of the Sign-Perturbed Sums Identification Method: Scalar Case, 22nd IFAC World Congress (World Congress of the International Federation of Automatic Control), Yokohama, Japan, July 9–14, 2023 [pdf]
        – Csáji, B. Cs.; Horváth, B.: Improving Kernel-Based Nonasymptotic Simultaneous Confidence Bands, 22nd IFAC World Congress (World Congress of the International Federation of Automatic Control), Yokohama, Japan, July 9–14, 2023 [pdf]
        – Kis, K. B.; Csempesz, J.; Csáji, B. Cs.: A Simultaneous Localization and Mapping Algorithm for Sensors with Low Sampling Rate and its Application to Autonomous Mobile Robots, 10th CIRP Conference on Digital Enterprise Technologies, 2021, pp. 154–159 [pdf]
        – Csáji, B. Cs.; Kis, K. B.; Kovács, A.: A Sampling-and-Discarding Approach to Stochastic Model Predictive Control for Renewable Energy Systems, 21st IFAC World Congress (1st Virtual IFAC World Congress), July 11–17, 2020, pp. 7142–7147 [pdf] [slides]
        – Csáji, B. Cs.; Tamás, A.: Semi-Parametric Uncertainty Bounds for Binary Classification, 58th IEEE Conference on Decision and Control (CDC), Nice, France, December 11–13, 2019, pp. 4427–4432 [pdf] [slides]
        – Carè, A.; Csáji, B. Cs.; Gerencsér, B.; Gerencsér, L.; Rásonyi, M.: Parameter-Dependent Poisson Equations: Tools for Stochastic Approximation in a Markovian Framework, 58th IEEE Conference on Decision and Control (CDC), Nice, France, December 11–13, 2019, pp. 2259–2264 [pdf]
        – Csáji, B. Cs.; Kis, K. B.: Distribution-Free Uncertainty Quantification for Kernel Methods by Gradient Perturbations, 58th European Conference on Machine Learning (ECML PKDD), Würzburg, Germany, September 16–20, 2019 [arxiv] [slides] [poster]
        – Gerencsér, L.; Csáji, B. Cs.; Sabanis, S.: Asymptotic Analysis of the LMS Algorithm with Momentum, 57th IEEE Conference on Decision and Control (CDC), Miami Beach, Florida, December 17–19, 2018, pp. 3062–3067 [pdf] [slides]
        – Csáji, B. Cs.: Non-Asymptotic Confidence Regions for Regularized Linear Regression Estimates, 20th European Conference on Mathematics for Industry (ECMI), Finite-Sample System Identification Minisymposium, Budapest, Hungary, June 18–22, 2018, Springer, pp. 605–611 [pdf]
        – Kolumbán, S.; Csáji, B. Cs.: Towards D-Optimal Input Design for Finite-Sample System Identification, 18th IFAC Symposium on System Identification (SYSID), Stockholm, Sweden, July 9–11, 2018, pp. 215–220 [pdf]
        – Carè, A.; Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Undermodelling Detection with Sign-Perturbed Sums, 20th IFAC World Congress, Toulouse, France, July 9–14, 2017, pp. 2799–2804 [pdf] [slides]
        – Carè, A.; Csáji, B. Cs.; Campi, M. C.: Sign-Perturbed Sums (SPS) with Asymmetric Noise: Robustness Analysis and Robustification Techniques, 55th IEEE Conference on Decision and Control (CDC), Las Vegas, Nevada, December 12–14, 2016, pp. 262–267 [pdf]
        – Csáji, B. Cs.: Score Permutation Based Finite Sample Inference for Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) Models, 19th International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, May 9–11, 2016, pp. 296–304 [pdf] [poster]
        – Volpe, V.; Csáji, B. Cs.; Carè, A.; Weyer, E.; Campi, M. C.: Sign-Perturbed Sums (SPS) with Instrumental Variables for the Identification of ARX Systems, 54th IEEE Conference on Decision and Control (CDC), Osaka, Japan, December 15–18, 2015, pp. 2115–2120 [arxiv]
        – Csáji, B. Cs.; Weyer, E.: Closed-Loop Applicability of the Sign-Perturbed Sums Method, 54th IEEE Conference on Decision and Control (CDC), Osaka, Japan, December 15–18, 2015, pp. 1441–1446 [pdf] [slides]
        – Csáji, B. Cs.; Kovács, A.; Váncza, J.: Adaptive Aggregated Predictions for Renewable Energy Systems, 2014 IEEE SSCI Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), Orlando, Florida, December 9–12, 2014, pp. 132–139 [pdf]
        – Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Strong Consistency of the Sign-Perturbed Sums Method, 53rd IEEE Conference on Decision and Control (CDC), Los Angeles, California, December 15–17, 2014, pp. 3352–3357 [pdf]
        – Weyer, E.; Csáji, B. Cs.; Campi, M. C.: Guaranteed Non-Asymptotic Confidence Ellipsoids for FIR Systems, 52nd IEEE Conference on Decision and Control (CDC), Florence, Italy, December 10–13, 2013, pp. 7162–7167 [pdf]
        – Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Sign-Perturbed Sums (SPS): A Method for Constructing Exact Finite-Sample Confidence Regions for General Linear Systems, 51st IEEE Conference on Decision and Control (CDC), Maui, Hawaii, December 10–13, 2012, pp. 7321–7326 [pdf]
        – Campi, M. C.; Csáji, B. Cs.; Garatti, S.; Weyer, E.: Certified System Identification: Towards Distribution-Free Results, 16th IFAC Symposium on System Identification (SYSID), Brussels, Belgium, July 11–13, 2012, pp. 245–255 [pdf]
        – Csáji, B. Cs.; Campi, M. C.; Weyer, E.: Non-Asymptotic Confidence Regions for the Least-Squares Estimate, 16th IFAC Symposium on System Identification (SYSID), Brussels, Belgium, July 11–13, 2012, pp. 227–232 [pdf]
        – Csáji, B. Cs.; Weyer, E.: Recursive Estimation of ARX Systems Using Binary Sensors with Adjustable Thresholds, 16th IFAC Symposium on System Identification (SYSID), Brussels, Belgium, July 11–13, 2012, pp. 1185–1190 [pdf] [slides]
        – Csáji, B. Cs.; Weyer, E.: System Identification with Binary Observations by Stochastic Approximation and Active Learning, 50th IEEE Conference on Decision and Control (CDC) & European Control Conference (ECC), Orlando, Florida, December 12–15, 2011, pp. 3634–3639 [pdf]
        – Ivanov, T.; Csáji, B. Cs.: Reproducing Kernels Preserving Algebraic Structure: A Duality Approach, 19th International Symposium on Mathematical Theory of Networks and Systems (MTMS), Budapest, Hungary, July 5–9, 2010, pp. 1161–1167 [pdf]
        – Csáji, B. Cs.; Jungers, R. M.; Blondel, V. D.: PageRank Optimization in Polynomial Time by Stochastic Shortest Path Reformulation, 21st International Conference on Algorithmic Learning Theory (ALT), Canberra, Australia, October 6–8, 2010, pp. 89–103 [pdf]
        – Csáji, B. Cs.; Monostori, L.: Adaptive Sampling Based Large-Scale Stochastic Resource Control, 21st National Conference on Artificial Intelligence (AAAI), Boston, Massachusetts, July 16–20, 2006, pp. 815–820 [pdf]
    Selected Papers in Hungarian
        – Tamás, A.; Csáji, B. Cs.: Statisztikus tanluláselmélet I: Szupport vektor gépek (Statistical Learning Theory I: Support Vector Machines), Érintő: Elektronikus Matematikai Lapok (Tangent: Electronic Journal of Mathematics, János Bolyai Mathematical Society), Vol. 31, március, 2024 [link]
        – Csáji, B. Cs.: Antirealizmus a matematikában (Anti-Realism in Mathematics), Érintő: Elektronikus Matematikai Lapok (Tangent: Electronic Journal of Mathematics, János Bolyai Mathematical Society), Vol. 22, December, 2021 [link]
        – Tamás, A.; Csáji, B. Cs.: Sztochasztikus garanciák bináris klasszifikációhoz (Stochastic Guarantees for Binary Classification), Alkalmazott Matematikai Lapok (Applied Mathematical Journal of the Section of Mathematics, Hungarian Academy of Sciences), Vol. 37, No. 2, 2020 [pdf]
        – Csáji, B. Cs.: Szimmetria és konfidencia (Symmetry and Confidence), Alkalmazott Matematikai Lapok (Applied Mathematical Journal of the Section of Mathematics, Hungarian Academy of Sciences), Vol. 36, No. 2, 2019, pp. 271–278 [pdf]
        – Csáji, B. Cs.; Rédei, M.: A racionális demokratikus véleményösszegzés korlátairól (On the Limits of Rational Democratic Judgment Aggregation), Magyar Filozófiai Szemle (Hungarian Philosophical Review), Vol. 55, No. 2, 2011, pp. 97–121 [pdf]

 SOFTWARE DEVELOPMENT

        2000 – 2002 Chess AI: Pandora Chess Program, v0.44, C++, Visual Studio, Windows, Freeware [pdf]
        2000 Educational Software: OCR with Multilayer Perceptrons, Delphi, Windows, Freeware [pdf]

 LANGUAGE SKILLS

        –   Hungarian mother tongue
        –   English fluent; CEFR Level: C1, Certificate in Advanced English (CAE), British Council
        –   German good; CEFR Level: C1, Zentrale Mittelstufenprüfung (ZMP), Goethe Institute

 PHD STUDENTS

        – Bálint Horváth, Doctoral School of Mathematics and Computer Science, Budapest University of Technology and Economics (BME)
Research topics: kernel regression, simultaneous confidence bands, nonparametric inference, image processing, sequential optimization
Awards: Best Ph.D. Student Award, SZTAKI: Institute for Computer Science and Control, 2020, 2022
        – Ambrus Tamás, Doctoral School of Mathematics, Institute of Mathematics, Faculty of Science, Eötvös Loránd University (ELTE)
Research topics: binary classification, resampling methods, kernel mean embedding, independence tests, stochastic bandits
Awards: Best Ph.D. Student Award, SZTAKI: Institute for Computer Science and Control, 2021; Cooperative Doctoral Program (KDP)
        – Szabolcs Szentpéteri, Doctoral School of Computer Science, Faculty of Informatics, Eötvös Loránd University (ELTE)
Research topics: finite-sample system identification, indirect adaptive control, randomized algorithms, sample complexity
Awards: Best Ph.D. Student Award, SZTAKI: Institute for Computer Science and Control, 2023

 INFORMATION FOR STUDENTS

    Opportunities for students, with strong background in mathematics and computer science, interested in the theory of machine learning:
        – M.Sc. and third year B.Sc. students (studying in Budapest): there are opportunities to do research projects in machine learning, possibly leading to a TDK participation or to a (bachelor's or master's) thesis. Successful students may also have part-time [employment possibilities] at SZTAKI.
        – Prospective Ph.D. students: as examples of possible research directions, see the thesis topic proposals at ELTE or BME, such as the ones about [statistical learning] and [reinforcement learning]. Strong theoretical background, especially in probability and statistics, is fundamental.
        – International students applying for Stipendium Hungaricum scholarships: some doctoral schools [require] that the applicants should contact them instead of the potential supervisors. If you do contact me, please, send a detailed CV (with subjects / grades), as well as your master's thesis.

BALÁZS CsANÁD CsÁJI

[ Last Updated: April 20, 2024 ]