Literature Recommendations

Oct 2025

• Grokking in the Ising Model
  Karolina Hutchison, David Yevick
  arXiv:2510.25966
• Renormalization group for deep neural networks: Universality of learning and scaling laws
  Gorka Peraza Coppola, Moritz Helias, Zohar Ringel
  arXiv:2510.25553
• Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
  Jean Barbier, Francesco Camilli, et al.
  arXiv:2510.24616
• Exploring high-dimensional random landscapes: from spin glasses to random matrices, passing through simple chaotic systems
  Alessandro Pacco
  arXiv:2510.23138
• The Gravitational Aspect of Information: The Physical Reality of Asymmetric "Distance"
  Tomoi Koide, Armin van de Venn
  arXiv:2510.22664
• Statistics of correlations in nonlinear recurrent neural networks
  German Mato, Facundo Rigatuso, Gonzalo Torroba
  arXiv:2510.21742
• Dynamical mean field approach to associative memory model with non-monotonic transfer functions
  Yoshiyuki Kabashima, Kazushi Mimura
  arXiv:2510.19146
• On the relationship between equilibria and dynamics in large, random neuronal networks
  Xiaoyu Yang, Giancarlo La Camera, Gianluigi Mongillo
  arXiv:2510.19091
• A unified framework for divergences, free energies, and Fokker-Planck equations
  Anna L. F. Lucchi, Jean H. Y. Passos, et al.
  arXiv:2510.16690
• Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
  Cassidy Ashworth, Pietro Liò, Francesco Caso
  arXiv:2510.16591
• Entropy production and irreversibility in the linearized stochastic Amari neural model
  Dario Lucente, Giacomo Gradenigo, Luca Salasnich
  arXiv:2510.16422
• Entanglement Entropy from Correlation Functions of Scalar Fields in and out of Equilibrium
  Mrinal Kanti Sarkar, Saranyo Moitra, Rajdeep Sensarma
  arXiv:2510.15035
• Nonequilibrium steady states in bead-spring models: Entropy production and probability distributions
  Jetin E Thomas, Ramandeep S. Johal
  arXiv:2510.13453
• A nonequilibrium distribution for stochastic thermodynamics
  Jean-Luc Garden
  arXiv:2510.08315
• Ergodicity Breaking and High-Dimensional Chaos in Random Recurrent Networks
  Carles Martorell, Rubén Calvo, et al.
  arXiv:2510.07932
• What is the most optimal diffusion?
  Vasili Baranau
  arXiv:2510.07571
• Attention to Order: Transformers Discover Phase Transitions via Learnability
  Şener Özönder
  arXiv:2510.07401
• Thermodynamics of data
  Borko Stosic
  arXiv:2510.06818
• The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
  Alessandro Favero
  arXiv:2510.06106
• Computing frustration and near-monotonicity in deep neural networks
  Joel Wendin, Erik G. Larsson, Claudio Altafini
  arXiv:2510.05286
• Learning Linear Regression with Low-Rank Tasks in-Context
  Kaito Takanami, Takashi Takahashi, Yoshiyuki Kabashima
  arXiv:2510.04548
• Minimal-Dissipation Learning for Energy-Based Models
  Jeff Hnybida, Simon Verret
  arXiv:2510.03137
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
  Runqian Wang, Yilun Du
  arXiv:2510.02300
• Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
  Sota Nishiyama, Masaaki Imaizumi
  arXiv:2510.01930
• Combining complex Langevin dynamics with score-based and energy-based diffusion models
  Gert Aarts, Diaa E. Habibi, et al.
  arXiv:2510.01328
• Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
  Blake Bordelon, Mary I. Letey, Cengiz Pehlevan
  arXiv:2510.01098
• Spin glasses and the Parisi formula
  Jean-Christophe Mourrat
  arXiv:2510.01054