George Matheos

George Matheos

Undergraduate AI Researcher

UC Berkeley

Biography

I’m a 4th year undergraduate at UC Berkeley studying math and computer science. I’m graduating from Berkeley in May, and in September I will begin as a PhD student at MIT, in computer science. I do artificial intelligence research advised by Stuart Russell and Vikash Mansinghka. From 2020-2021, I worked full-time as a researcher at the MIT Probabilistic Computing Project. My research focuses on probabilistic programming and well-founded AI. For more information, see my CV.

Interests
  • Artificial Intelligence
  • Probabilistic Programming
Education

  • PhD in Computer Science (program begins September 2023)

    Massachusetts Institute of Technology

  • BA in Mathematics and Computer Science, 2023

    University of California, Berkeley

Publications

Alexander K. Lew, George Matheos, Tan Zhi-Xuan, Matin Ghavamizadeh, Nishad Gothoskar, Stuart Russell, Vikash K. Mansinghka (2023). SMCP3: SMC with Probabilistic Program Proposals. AISTATS, 2023.

PDF Code Poster Video

George Matheos, Andrew D. Bolton, McCoy Becker, Cameron Freer, Vikash K. Mansinghka (2022). Brain computation as fast spiking neural Monte Carlo inference in probabilistic programs. Poster at NAISys, at CSHL, Aug 2022. Poster at MIT Quest for Intelligence, Nov 2022. Paper in preparation for submission to a top-tier interdisciplinary conference.

PDF Poster

George Matheos, Alexander K. Lew, Matin Ghavamizadeh, Stuart Russell, Marco Cusumano-Towner, Vikash K. Mansinghka (2020). Transforming Worlds: Automated Involutive MCMC for Open Universe Probabilistic Programs. AABI, 2020.

PDF Cite Code Poster

Contact

  • georgematheos AT berkeley DOT edu