2 code implementations • 2 May 2023 • Jialin Mao, Itay Griniasty, Han Kheng Teoh, Rahul Ramesh, Rubing Yang, Mark K. Transtrum, James P. Sethna, Pratik Chaudhari
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training.
no code implementations • 21 Sep 2021 • Cody Petrie, Christian Anderson, Casie Maekawa, Travis Maekawa, Mark K. Transtrum
We consider how mathematical models enable predictions for conditions that are qualitatively different from the training data.
2 code implementations • 2 May 2017 • Henry H. Mattingly, Mark K. Transtrum, Michael C. Abbott, Benjamin B. Machta
We use the language of uninformative Bayesian prior choice to study the selection of appropriately simple effective models.
1 code implementation • 22 Sep 2014 • Mark K. Transtrum, Gus Hart, Peng Qiu
We introduce Information Topology in analogy with information geometry as characterizing the "abstract model" of which statistical models are realizations.
Data Analysis, Statistics and Probability Materials Science Statistics Theory Statistics Theory
3 code implementations • 27 Jan 2012 • Mark K. Transtrum, James P. Sethna
We introduce several improvements to the Levenberg-Marquardt algorithm in order to improve both its convergence speed and robustness to initial parameter guesses.
Data Analysis, Statistics and Probability Computational Physics