no code implementations • 2 Mar 2024 • Jason Z. Kim, Nicolas Perrin-Gilbert, Erkan Narmanli, Paul Klein, Christopher R. Myers, Itai Cohen, Joshua J. Waterfall, James P. Sethna
Natural systems with emergent behaviors often organize along low-dimensional subsets of high-dimensional spaces.
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.
2 code implementations • 31 Oct 2022 • Rahul Ramesh, Jialin Mao, Itay Griniasty, Rubing Yang, Han Kheng Teoh, Mark Transtrum, James P. Sethna, Pratik Chaudhari
We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-supervised and contrastive learning.
no code implementations • 25 May 2017 • Lorien X. Hayden, Alexander A. Alemi, Paul H. Ginsparg, James P. Sethna
Neural networks have been shown to have a remarkable ability to uncover low dimensional structure in data: the space of possible reconstructed images form a reduced model manifold in image space.
1 code implementation • 20 Mar 2015 • Lorien X. Hayden, Ricky Chachra, Alexander A. Alemi, Paul H. Ginsparg, James P. Sethna
A classification of companies into sectors of the economy is important for macroeconomic analysis and for investments into the sector-specific financial indices and exchange traded funds (ETFs).
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