The goal of Physics \u2229 ML is to bring together researchers from machine learning and physics to learn from each other and push research forward together. In this inaugural edition, we will especially highlight some amazing progress made in string theory with machine learning and in the understanding of deep learning from a physical angle. Nevertheless, we invite a cast with wide ranging expertise in order to spark new ideas. Plenary sessions from experts in each field and shorter specialized talks will introduce existing research. We will hold moderated discussions and breakout groups in which participants can identify problems and hopefully begin new collaborations in both directions. For example, physical insights can motivate advanced algorithms in machine learning, and analysis of geometric and topological datasets with machine learning can yield critical new insights in fundamental physics.<\/p>\n
Session 2 – Applying physical insights to ML<\/p>\n
2:45 PM\u20134:05 PM
\nShort talks<\/p>\n
Neural tangent kernel and the dynamics of large neural nets by Clement Hongler
\nOn the global convergence of gradient descent for over-parameterized models using optimal transport by L\u00e9na\u00efc Chizat
\nPathological spectrum of the Fisher information matrix in deep neural networks by Ryo Karakida
\nQ&A
\nFluctuation-dissipation relation for stochastic gradient descent by Sho Yaida
\nFrom optimization algorithms to continuous dynamical systems and back by Rene Vidal
\nThe effect of network width on stochastic gradient descent and generalization by Daniel Park
\nQ&A
\nShort certificates for symmetric graph density inequalities by Rekha Thomas
\nGeometric representation learning in hyperbolic space by Maximilian Nickel
\nThe fundamental equations of MNIST by Cedric Beny
\nQ&A
\nTalk title to be announced by Paul Smolensky
\nMulti-scale deep generative Networks for Bayesian inverse problems by Pengchuan Zhang
\nVariational quantum classifiers in the context of quantum machine learning by Alex Bocharov
\nQ&A<\/p>\n