Cameron Freer

Postdoctoral Associate, MIT Brain and Cognitive Sciences
Research Scientist, Gamalon Labs

Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology

32 Vassar Street
Cambridge, MA 02139




My research interests are in the computability and complexity theory of probabilistic inference, computable probability theory, the model theory of graphs and graph limits, and the physics of causality and computation.


Curriculum Vitae



Feedback Turing computability, and Turing computability as feedback, with Nate Ackerman and Robert Lubarsky, in Proceedings of the 30th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS 2015), 2015.

Invariant measures via inverse limits of finite structures, with Nate Ackerman, Jaroslav Nešetřil, and Rehana Patel, to appear in European Journal of Combinatorics. arXiv:1310.8147.

Algorithmic aspects of Lipschitz functions, with Bjørn Kjos-Hanssen, André Nies, and Frank Stephan, Computability 3, 45–61, 2014. arXiv:1402.2429.

Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence, with Daniel Roy and Joshua Tenenbaum, in Turing's Legacy: Developments from Turing's Ideas in Logic, ed. Rod Downey, ASL Lecture Notes in Logic, Cambridge University Press, 2014. arXiv:1212.4799.

Randomness extraction and asymptotic Hamming distance, with Bjørn Kjos-Hanssen, Selected Papers of the Ninth International Conference on Computability and Complexity in Analysis (CCA 2012), Logical Methods in Computer Science, 2013. arXiv:1008.0821.

Causal entropic forces, with Alexander Wissner-Gross, Physical Review Letters 110, 168702, 2013. Supplemental Material.

A notion of a computational step for Partial Combinatory Algebras, with Nate Ackerman, in Proceedings of the 10th Annual Conference on Theory and Applications of Models of Computation (TAMC 2013), LNCS Vol. 7876, 133–143, 2013.

Computable de Finetti measures, with Daniel Roy, Annals of Pure and Applied Logic 163, no. 5, 530–546, 2012. arXiv:0912.1072.

Noncomputable conditional distributions, with Nate Ackerman and Daniel Roy, in Proceedings of the 26th Annual IEEE Symposium on Logic in Computer Science (LICS 2011), 107–116, 2011.

Relativistic statistical arbitrage, with Alexander Wissner-Gross, Physical Review E 82, 056104, 2010.

Posterior distributions are computable from predictive distributions, with Daniel Roy, in Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Journal of Machine Learning Research (JMLR) Workshop and Conference Proceedings 9, 2010.

Computable exchangeable sequences have computable de Finetti measures, with Daniel Roy, in Mathematical Theory and Computational Practice, Proceedings of Computability in Europe (CiE 2009), LNCS Vol. 5635, 218–231, 2009.



On computability and disintegration, with Nate Ackerman and Daniel Roy. arXiv:1509.02992.

A classification of orbits admitting a unique invariant measure, with Nate Ackerman, Aleksandra Kwiatkowska, and Rehana Patel. arXiv:1412.2735.

An iterative step-function estimator for graphons, with Diana Cai and Nate Ackerman. arXiv:1412.2129.

Invariant measures concentrated on countable structures, with Nate Ackerman and Rehana Patel. arXiv:1206.4011.

On the computability of conditional probability, with Nate Ackerman and Daniel Roy. arXiv:1005.3014.


PhD Thesis

Models with High Scott Rank, PhD thesis, Harvard University, 2008.



System and method for relativistic statistical securities trading, with Alexander Wissner-Gross, U.S. Patent 8,635,133 (2014).


MIT home page