Dr. Tom Schaul

Research Scientist, NYU Courant Institute of Mathematical Sciences
New York City, New York, United States

Research field: Computer and Information Science - Artificial Intelligence
Recurrent Neural Networks, Reinforcement Learning, Artificial Curiosity, Optimization, AI in Games.

Publications

Journal Article (4)
- Vincent Graziano, Tobias Glasmachers, Tom Schaul et al. (2011) Artificial Curiosity for Autonomous Space Exploration, 41-51. In Acta Futura 1 (4).
- Anderson Alvarenga de Moura Meneses, Christiano Jorge Gomes Pinheiro, Paola Rancoita et al. (2010) Assessment of neural networks training strategies for histomorphometric analysis of synchrotron radiation medical images. In Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment.
  http://dx.doi.org/10.1016/j.nima.2010...
- Thomas Rückstieß, Frank Sehnke, Tom Schaul et al. (2010) Exploring Parameter Space in Reinforcement Learning, 14-24. In Paladyn Journal of Behvioral Robotics 1 (1).
  Download PDF (1.41 MB)
- Tom Schaul, Justin Bayer, Daan Wierstra et al. (2010) PyBrain, 743−746. In Journal of Machine Learning Research.
  Download PDF (69.47 KB)
Book Section (1)
- Tom Schaul (2013) Optimization with Surrogate Models. In Numerical Methods for Metamaterial Design.
  http://books.google.com/books?id=ED5O...
Conference Proceedings (33)
- Yi Sun, Faustino Gomez, Tom Schaul et al. (2013) A Linear Time Natural Evolution Strategy for Non-Separable Functions. In Proceedings of the Genetic and Evolutionary Computation Conference.
- Tom Schaul, Yann LeCun (2013) Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients. In International Conference on Learning Representations.
  Download PDF (1.43 MB)
- Tom Schaul, Yann LeCun (2013) Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients. In International Conference on Learning Representations.
  Download PDF (1.43 MB)
- Tom Schaul, Mark B Ring (2013) Better Generalization with Forecasts. In International Joint Conference on Artificial Intelligence (IJCAI).
  Download PDF (699.32 KB)
- Tom Schaul, Sixin Zhang, Yann LeCun (2013) No More Pesky Learning Rates. In International Conference on Machine Learning (ICML).
  Download PDF (563.98 KB)
  
  Download PDF (902.09 KB)
- Tom Schaul (2012) Benchmarking Exponential Natural Evolution Strategies on the Noiseless and Noisy Black-box Optimization Testbeds. In Black-box Optimization Benchmarking Workshop, Genetic and Evolutionary Computation Conference.
  Download PDF (1.77 MB)
- Tom Schaul (2012) Benchmarking Natural Evolution Strategies with Adaptation Sampling on the Noiseless and Noisy Black-box Optimization Testbeds. In Black-box Optimization Benchmarking Workshop, Genetic and Evolutionary Computation Conference.
  Download PDF (1.8 MB)
- Tom Schaul (2012) Benchmarking Separable Natural Evolution Strategies on the Noiseless and Noisy Black-box Optimization Testbeds. In Black-box Optimization Benchmarking Workshop, Genetic and Evolutionary Computation Conference.
  Download PDF (1.76 MB)
- Tom Schaul (2012) Comparing Natural Evolution Strategies to BIPOP-CMA-ES on Noiseless and Noisy Black-box Optimization Testbeds. In Black-box Optimization Benchmarking Workshop, Genetic and Evolutionary Computation Conference.
  Download PDF (1.5 MB)
- Tom Schaul, Sixin Zhang, Yann LeCun (2012) Decoupling the Data Geometry from the Parameter Geometry for Stochastic Gradients. In Snowbird Learning Workshop.
  Download PDF (98.33 KB)
- See all
Report (4)
- Tom Schaul, Sixin Zhang, Yann LeCun (2012) No More Pesky Learning Rates.
  http://arxiv.org/abs/1206.1106
  
  Download PDF (955.68 KB)
- Yi Sun, Faustino Gomez, Tom Schaul et al. (2011) A Linear Time Natural Evolution Strategy for Non-Separable Functions.
  http://arxiv.org/abs/1106.1998
  
  Download PDF (592.97 KB)
- Tom Schaul, Julian Togelius, Jürgen Schmidhuber (2011) Measuring Intelligence through Games.
  http://arxiv.org/abs/1109.1314
- Daan Wierstra, Tom Schaul, Tobias Glasmachers et al. (2011) Natural Evolution Strategies.
  http://arxiv.org/abs/1106.4487
Thesis (2)
- Tom Schaul (2011) Studies in Continuous Black-box Optimization.
  Download PDF (2.44 MB)
- Tom Schaul (2005) Evolving a compact , concept-based Sokoban solver.
  Download PDF (438.83 KB)
Encyclopedia Article (1)
- Tom Schaul, Jürgen Schmidhuber (2010) Metalearning, 4650. 5 (6).
  http://www.scholarpedia.org/article/M...

Awards and Grants

Aug 2011

Solomonoff Student Prize
Mar 2010

Kurzweil Best AGI Paper Award
Jul 2009

GECCO Best Paper Award
Jul 2000

International Mathematics Olympiad: Bronze Medal

Biographical Information

I am doing a postdoc in machine learning at NYU in Yann LeCun's lab. Just recently I completed my Ph.D. at IDSIA/TU Munich, supervised by Jürgen Schmidhuber. I grew up in Luxembourg, and completed my studies in computer engineering at the EPFL in Switzerland, at Columbia University and at the University of Waterloo. I work on (modular) reinforcement learning, black-box optimization, (deep and/or recurrent) neural networks, artificial curiosity and related topics.

CV

Professional Experience

2011 - Present

Research Scientist at NYU Courant Institute of Mathematical Sciences
New York, New York, United States

Feb 2007 - Aug 2011

PhD student at IDSIA
Lugano, Switzerland

Education

Feb 2007 - Aug 2011

Technische Universität München in Munich, Germany
Dr. rer. nat.

Oct 2000 - May 2005

EPFL - Swiss Federal Institute of Technology in Lausanne, Switzerland
MSc

Consulting Services

Baum Research Enterprises

Contact Information

Webpage:

http://www.idsia.ch/~tom/

See all

18 Contacts

Public Groups

Public groups Tom is a member of

Public groups Tom is following

Not following any groups yet.
Find new public groups.

Destinations

Loading Map ...

Show All Cities

New York City, New York, United States

Main City