Less bored by this than I used to be, since it turns out that not everything is ideal gases and spin glasses, as cute as classical statmech is.
See thermodynamics of computation, statistical mechanics of statistics, statistical mechanics of games, thermodynamics of life, quantum information etc.
1 References
Baldassi, Borgs, Chayes, et al. 2016. “Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes.” Proceedings of the National Academy of Sciences.
Barbier. 2015. “Statistical Physics and Approximate Message-Passing Algorithms for Sparse Linear Estimation Problems in Signal Processing and Coding Theory.” arXiv:1511.01650 [Cs, Math].
Castellani, and Cavagna. 2005. “Spin-Glass Theory for Pedestrians.” Journal of Statistical Mechanics: Theory and Experiment.
Ghavasieh, Nicolini, and De Domenico. 2020. “Statistical Physics of Complex Information Dynamics.” Physical Review E.
Lin, and Tegmark. 2016a. “Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language.” arXiv:1606.06737 [Cond-Mat].
———. 2016b. “Why Does Deep and Cheap Learning Work so Well?” arXiv:1608.08225 [Cond-Mat, Stat].
Mehta, and Schwab. 2014. “An Exact Mapping Between the Variational Renormalization Group and Deep Learning.”
Onsager, and Machlup. 1953. “Fluctuations and Irreversible Processes.” Physical Review.
Pavon. 1989. “Stochastic Control and Nonequilibrium Thermodynamical Systems.” Applied Mathematics and Optimization.
Shwartz-Ziv, and Tishby. 2017. “Opening the Black Box of Deep Neural Networks via Information.” arXiv:1703.00810 [Cs].
Wiatowski, Grohs, and Bölcskei. 2018. “Energy Propagation in Deep Convolutional Neural Networks.” IEEE Transactions on Information Theory.