1.4k citations · 7.9k across the 69 of their papers we have counts for
70 papers
Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
Batu El, Jinhee Paeng, Fatih Dinc +7
AI agents increasingly operate as part of interacting systems rather than in isolation. As agents exchange information and jointly make decisions, their interactions can improve co…
Entanglement and replica symmetry breaking in a driven-dissipative quantum spin glass
Brendan P. Marsh, Ronen M. Kroeze, Surya Ganguli +3
We describe simulations of the quantum dynamics of a confocal cavity QED system that realizes an intrinsically driven-dissipative spin glass. A close connection between open quantu…
Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression
Allan Raventós, Mansheej Paul, Feng Chen +1
Pretrained transformers exhibit the remarkable ability of in-context learning (ICL): they can learn tasks from just a few examples provided in the prompt without updating any weigh…
Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
Feng Chen, Daniel Kunin, Atsushi Yamamura +1
In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducin…
Singular Vectors of Sums of Rectangular Random Matrices and Optimal Estimators of High-Rank Signals: The Extensive Spike Model
Itamar D. Landau, Gabriel C. Mel, Surya Ganguli
Across many disciplines from neuroscience and genomics to machine learning, atmospheric science and finance, the problems of denoising large data matrices to recover signals obscur…
Neural networks: from the perceptron to deep nets
Marylou Gabrié, Surya Ganguli, Carlo Lucibello +1
Artificial networks have been studied through the prism of statistical mechanics as disordered systems since the 80s, starting from the simple models of Hopfield's associative memo…