Nonequilibrium thermodynamics of self-supervised learning

Abstract

Self-supervised learning (SSL) of energy based models has an intuitive relation to equilibrium thermodynamics because the softmax layer, mapping energies to probabilities, is a Gibbs distribution. However, in what way SSL is a thermodynamic process? We show that some SSL paradigms behave as a thermodynamic composite system formed by representations and self-labels in contact with a nonequilibrium reservoir. Moreover, this system is subjected to usual thermodynamic cycles, such as adiabatic expansion and isochoric heating, resulting in a generalized Gibbs ensemble (GGE). In this picture, we show that learning is seen as a demon that operates in cycles using feedback measurements to extract negative work from the system. As applications, we examine some SSL algorithms using this idea.

6 pages, 1 figure

References in corpus (6)

• Self-supervised Pretraining of Visual Features in the Wild
• Learning physical properties of liquid crystals with deep convolutional neural networks
• Estimating physical properties from liquid crystal textures via machine learning and complexity-entropy methods
• Stochastic Thermodynamics of Learning
• Spectral Dynamics of Learning Restricted Boltzmann Machines
• Thermodynamic efficiency of learning a rule in neural networks