BALÁZS CsANÁD CsÁJI

 

[ Positions ]    [ Degrees ]    [ Interests ]    [ Visits ]    [ Teaching ]    [ Projects ]    [ Awards ]    [ Publications ]    [ Programs ]    [ Languages ]

OPPORTUNITIES FOR STUDENTS

 

CURRENT POSITION

 

 

Senior Research Fellow
Engineering and Management Intelligence Laboratory (EMI),
Institute for Computer Science and Control (SZTAKI),
Hungarian Academy of Sciences (MTA)

Room K317, Central Building
13-17 Kende utca, XI. kerület
Budapest, Hungary, H 1111

Phone: (+36) 1-279-6231
Fax: (+36) 1-279-7503
balazs
[dot] csaji [at] sztaki [dot] mta [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"

FIELDS OF INTEREST

      Computer Science

Machine Learning, Resource Allocation, Randomized Algorithms

      Control Engineering

System Identification, Robust- and Stochastic Control

      Applied Mathematics

Statistics, Probabilistic Models, Stochastic Approximation, Operations Research

      Analytic Philosophy

Philosophy of Science, 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 Ličge, 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, UK

     2007

Alberta Ingenuity Center for Machine Learning, Department of Computing Science, University of Alberta, Canada

TEACHING AND PRESENTATIONS

  

  Teaching Activity

     2015 – 2017 Stochastic Models and Adaptive Algorithms, PhD School of Computer Science, Eötvös Loránd University (ELTE), Hungary
     2013 – 2014 Mathematical Programming (main organizer), Institute for Computer Science and Control (SZTAKI), Hungary
     2012    Sem1 Probability and Random Models (ELEN90054, with Girish Nair), School of Engineering, University of Melbourne, Australia
     2005 – 2006 Markov Decision Processes (organized by Cs. Szepesvári), Institute for Computer Science and Control (SZTAKI), Hungary
     2002 Theory of Operating Systems, Department of Information Systems, Eötvös Loránd University (ELTE), Hungary

     2000 – 2002

Programming Methodology, Department of Software Technology, Eötvös Loránd University (ELTE), Hungary

  Selected Slides

     2012 Distribution-Free System Identification: Exact-, Non-Asymptotic Confidence Regions, Faculty of Electrical Engineering,
Computer Science, and Mathematics, University of Paderborn, Germany, 16 July 2012 [pdf]
     2010 Introduction to Markov Decision Processes, Department of Electrical Engineering, University of Melbourne, Australia [pdf]
     2010 PageRank Optimization in Polynomial Time by Stochastic Shortest Path Reformulation, 21st International Conference on
Algorithmic Learning Theory (ALT), Australian National University (ANU), Canberra, Australia [pdf]
     2009 A Machine Learning Approach to Stochastic Resource Control, Poster, DYSCO Study Day, Mons, Belgium [pdf]
     2008 Learning in Changing Environments: Reinforcement Learning in Environments with Asymptotically Bounded Variation,
University College London (UCL), London, United Kingdom  [pdf]
     2006 Introduction to Off-Policy Learning, RL Seminar, SZTAKI, Budapest, Hungary [pdf]

     2005

Introduction to Temporal Difference Learning (Hungarian Slides), RL Seminar, SZTAKI, Budapest, Hungary [pdf]

     2004

Intuitionism in Mathematics (Philosophy of Mathematics), HalSzem, ELTE, Budapest, Hungary [pdf] Handout [pdf]

PROJECT PARTICIPATIONS

 

  European Projects

     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, 5th Framework, EU

  National Projects

     2014 2016 Analytical Module for a Wireless Multi-Sensor Network (Principal Investigator), comissioned by GE Hungary Ltd.
     2011 2014 E+Grid: An Embedded System for Optimizing Energy Positive Public Lighting Service, NFÜ, Hungary
     2011 2012 Distribution-Free System Identification (Principal Investigator), ARC, Australia
     2009 2011 Algorithms for Change Detection Based on Finite Sample System Identification Theory, ARC, Australia
     2008 2010 Production Structures as Complex Adaptive Systems, OTKA, Hungary
     2004 2007 VITAL: Real-Time, Cooperative Enterprises, NKFP, Hungary
     2005 2007 Modeling, Planning and Control of Distributed, Modular Production Structures, OTKA, Hungary

  University Projects

     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 and Semmelweis University, Hungary

AWARDS, SCHOLARSHIPS AND MEMBERSHIPS

 

  Honors and Awards

     2016 Béla Gyires Prize (Applied Mathematics), Section of Mathematics, 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 Junior Award for Research Excellence (Mathematical Sciences), Hungarian Academy of Sciences (MTA)
     2009, 16 Publication Award (2x), Institute for Computer Science and Control (SZTAKI)
     2006 Young Researcher Prize, Institute for Computer Science and Control (SZTAKI)
     2006 Best Paper Award, International Workshop on Emergent Synthesis (IWES), University of Tokyo
     2004 Best Ph.D. Student Award, Institute for Computer Science and Control (SZTAKI)
     2004, 09, 15 Prize for Excellence (3x), Institute for Computer Science and Control (SZTAKI)
     2000 First Prize, Section of Informatics, Scientific Student Conference (TDK), Eötvös Loránd University (ELTE)

  Scholarships

     2016 2019 János Bolyai Research Fellowship (2nd), Hungarian Academy of Sciences (MTA)
     2012 2015 János Bolyai Research Fellowship (1st), 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, Faculty of Informatics, Eötvös Loránd University (ELTE)
     2000 2001 Research Scholarship (Artificial Intelligence), Pázmány-Eötvös Foundation

  Memberships

     2015 Hungarian Operations Research Society (MOT)
     2014 International Federation of Automatic Control (IFAC)

     2013 –

Institute of Electrical and Electronic Engineers (IEEE), Control Systems Society (CSS)

BIBLIOMETRICS

 

All publications: 62

Independent citations*: 500+

Cumulative impact factor: 27+

Erdős number**: 3

Journal articles: 19

Book chapters & LNCS/AI: 6

Conference & workshop papers: 37

Invited talks: 15

* A [citation] is independent if none of the authors of the citing paper is an author of the cited paper

** [proof]

SELECTED PUBLICATIONS

     System Identification: Finite Sample & Distribution-Free

      – Weyer, E.; Campi, M. C.; Csáji, B. Cs: Asymptotic Properties of SPS Confidence Regions, Automatica, Elsevier, 2017 [in press]

      – 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, Vol. 69, 2015, 169181 [pdf]

      – 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 2016), Las Vegas, Nevada, December 12-14, 2016, pp. 262–267 [pdf]

      – Csáji, B. Cs.; Weyer, E.: Closed-Loop Applicability of the Sign-Perturbed Sums Method, 54th IEEE Conference on Decision and Control
        
(CDC 2015), Osaka, Japan, December 15-18, 2015, pp. 1441–1446 [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 2014), 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 2013), Florence, Italy, 2013, pp. 71627167 [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 2012), Maui, Hawaii, 2012, pp. 73217326 [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 2012), Brussels, Belgium, July 1113, 2012, pp. 245255 [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 2012), Brussels, Belgium, July 1113, 2012, pp. 227232 [pdf]

     System Identification: Quantized & Recursive

      – Csáji, B. Cs.; Weyer, E.: Recursive Estimation of ARX Systems Using Binary Sensors with Adjustable Thresholds, 16th IFAC Symposium
        
on System Identification (SYSID 2012), Brussels, Belgium, July 1113, 2012, pp. 11851190 [pdf]

      – Csáji, B. Cs.; Weyer, E.: System Identification with Binary Observations by Stochastic Approximation and Active Learning, 50th IEEE
        
Conference on Decision and Control (CDC 2011) & European Control Conference (ECC), Orlando, Florida, 2011 [pdf]

     Machine Learning: Markov Decision Processes, Kernels & Applications

      – 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, 2016, pp. 296-304 [pdf] [poster]

      – Ivanov, T.; Csáji, B. Cs.: Reproducing Kernels Preserving Algebraic Structure: A Duality Approach, Proceedings of the 19th International

         Symposium on Mathematical Theory of Networks and Systems (MTNS 2010), Budapest, Hungary, July 5–9, 2010, pp. 11611167 [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, 1679–1709 [link] [pdf]

      – Csáji, B. Cs.; Küng, J.; Palkoska, J.; Wagner, R.: On the Automation of Similarity Information Maintenance in Flexible Query Answering

         Systems; Proceedings of the 15th International Conference on Database and Expert Systems Applications (DEXA 2004), August 30

         September 3, Zaragoza, Spain, Lecture Notes in Computer Science (LNCS), Vol. 3180, Springer, 2004, pp. 130–140 [link]

     Network Theory: PageRank Optimization & Mobility Analysis

      – Csáji, B. Cs.; Jungers, R. M.; Blondel, V. D.: PageRank Optimization by Edge Selection, Discrete Applied Mathematics (DAM),

         Elsevier, Volume 169, 2014, 73–87 [arXiv] [link]

      Csáji, B. Cs.; Browet, A.; Traag, V. A.; Delvenne, J-C.; Huens, E.; Van Dooren, P.; Smoreda, Z.; Blondel, V. D.: Exploring Mobility of

         Mobile Phone Users, Physica A: Statistical Mechanics and its Applications, Elsevier, Vol. 392, Issue 6, 2013, 14591473 [link]

      – Csáji, B. Cs.; Jungers, R.M.; Blondel, V.D.: PageRank Optimization in Polynomial Time by Stochastic Shortest Path Reformulation,

         Proceedings of the 21st International Conference on Algorithmic Learning Theory (ALT 2010), Lecture Notes in Computer Science

         (LNCS), Vol. 6331, Springer, The Australian National University, Canberra, Australia, October 6–8, 2010, pp. 89–103 [link] [pdf]

     Renewable Energy Systems: Aggregated Forecasts & Model Predictive Control

      Csáji, B. Cs.; Kovács, A.; Váncza, J.: Adaptive Aggregated Predictions for Renewable Energy Systems; 2014 IEEE Symposium on

         Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2014), part of IEEE Symposium Series on Computational

         Intelligence (SSCI 2014), Orlando, Florida, December 9-12, 2014 [pdf]

      Csáji, B. Cs.; Kovács, A.; Váncza, J.: Prediction and Robust Control of Energy Flow in Renewable Energy Systems, 19th World
         Congress
of the International Federation of Automatic Control (IFAC-WC 2014), Cape Town, South Africa, 2014 [pdf]

     Resource Allocation: Adaptive Algorithms & Stochastic Scheduling

      Csáji, B. Cs.; Monostori, L.: Adaptive Stochastic Resource Control: A Machine Learning Approach, Journal of Artificial Intelligence

         Research (JAIR), AAAI Press, Vol. 32, 2008, 453–486 [link] [pdf]

      Csáji, B. Cs.; Monostori, L.; Kádár, B.: Reinforcement Learning in a Distributed Market-Based Production Control System, Advanced

         Engineering Informatics (formerly: Journal of Artificial Intelligence in Engineering), Elsevier, Vol. 20, 2006, 279–288 [link]

      Csáji, B. Cs.; Monostori, L.: Adaptive Sampling Based Large-Scale Stochastic Resource Control, Proceedings of the

         21st National Conference on Artificial Intelligence (AAAI 2006), July 16–20, Boston, Massachusetts, 2006, pp. 815–820 [pdf]

      Csáji, B. Cs.; Monostori, L.: Adaptive Algorithms in Distributed Resource Allocation, Proceedings of the 6th International Workshop

         on Emergent Synthesis (IWES 2006), Kashiwa, The University of Tokyo, Japan, August 18–19, 2006. pp. 69–75 Best Paper Award

     Production Processes: Cooperative Control & Adaptive Manufacturing

      Monostori, L.; Valckenaers, P.; Dolgui, A.; Panetto, H.; Brdys, M.; Csáji, B. Cs.: Cooperative Control in Production and Logistics,

         Annual Reviews in Control (ARC), Elsevier, Volume 39, 2015, pp. 12–29 [arXiv] [link]

      Monostori, L.; Csáji, B. Cs.; Kádár, B.; Pfeiffer, A.; Ilie-Zudor, E.; Kemény, Zs.; Szathmári, M.: Towards Adaptive and Digital

         Manufacturing, Annual Reviews in Control (ARC), Elsevier, Vol. 34, 2010, pp. 118–128 [link]

      Schuh, G.; Monostori, L.; Csáji, B. Cs.; Döring, S.: Complexity-Based Modeling of Reconfigurable Collaborations in Production Industry,

         Annals of the CIRP: Manufacturing Technology, Elsevier, Vol. 57., 2008, pp. 445450

      – Monostori, L.; Csáji, B. Cs.: Stochastic Dynamic Production Control by Neurodynamic Programming, Annals of the CIRP: Manufacturing

         Technology, Elsevier, Vol. 55, No. 1, 2006, 473478

     Philosophy of Science: Social Choice Theory & Logic

      Csáji, B. Cs.; Rédei, M.: On the Constraints of Rational Judgment Aggregation, Hungarian Philosophical Review, 2011 (2), 97121 [link]

      Csáji, B. Cs.: In Defense of the Symmetry of True and False; Proceedings of the 6th Interdisciplinary Symmetry Congress and Exhibition,

         International Society for the Interdisciplinary Study of Symmetry, October 22–29, Tihany, Hungary, 2004, pp. 46–49 [pdf]

 

PROGRAM DEVELOPMENT

     2000 2002 

Chess AI: Pandora Chess Program v0.44, C++, Visual Studio, Windows, 32 bit, Freeware [zip]

     2000    

Educational Software: OCR with Multilayer Perceptrons, Delphi, Windows, 32 bit, Freeware [zip]

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

OPPORTUNITIES FOR STUDENTS

     Students interested in statistical machine learning, with strong background in mathematics and computer science, should consider:

      MSc and BSc students (studying in Budapest): part-time employment possibilities for enrolled university students.

      Prospective PhD students: available funding from September 2017. Also see the [thesis topic proposal] at ELTE-IK.

 

 

BALÁZS CsANÁD CsÁJI

[ Last Updated: March 21, 2017 ]