Gábor Balázs

I am a computer scientist interested in machine learning applications and research, especially in convex regression, mathematical optimization, and sequential decision making. I received my MSc at the Eötvös Lóránd University, and my PhD in Statistical Machine Learning at the University of Alberta under the supervision of Csaba Szepesvári and Dale Schuurmans.

Currently I am a freelance machine learning consultant, working on scientific research, quantitative algo-trading for Causality Group, and sometimes on some other projects. I live in Cartagena (Spain) with my wife Gema who is a writer and an illustrator.

Publications

• Adaptively partitioning max-affine estimators for convex regression,
  Gábor Balázs, AISTATS 2022,
  
  
• Convex regression: theory, practice, and applications,
  Gábor Balázs, PhD thesis, University of Alberta, 2016,
  
  
• Near-optimal max-affine estimators for convex regression,
  Gábor Balázs, András György, Csaba Szepesvári, AISTATS 2015,

Technical Reports

• Max-affine estimators for convex stochastic programming,
  Gábor Balázs, András György, Csaba Szepesvári, arXiv:1609.06331, 2016,
  
  
• Chaining bounds for empirical risk minimization,
  Gábor Balázs, András György, Csaba Szepesvári, arXiv:1609.01872, 2016,
  
  
• Cascade-Correlation Neural Networks: A Survey,
  Gábor Balázs, UofA Technical Report 2009,

Software (github.com/gabalz)

• Convex Regression (Python)
• Robot Segway Simulator (Java)
• RL-Glue Lisp Codec (Common Lisp)