A thermodynamic framework maps SGD stationary distributions in scale-invariant networks to ideal-gas behavior, with training hyperparameters acting as thermodynamic variables.
Another approach is to derive temperature directly Table 2: Notations used throughout the paper
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?
A thermodynamic framework maps SGD stationary distributions in scale-invariant networks to ideal-gas behavior, with training hyperparameters acting as thermodynamic variables.