Four characterizations of irreversibility in training algorithms are equivalent to leading order in step size and produce an emergent force that breaks reparametrization symmetries while favoring minimum entropy production trajectories.
Starting at θt, take one forward step and then one backward step with the sign of the step size reversed: θt+1 =θ t −ηU(θ t), ˜θt =θ t −ηU(θ t) +ηU(θ t+1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.stat-mech 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Thermodynamic Irreversibility of Training Algorithms
Four characterizations of irreversibility in training algorithms are equivalent to leading order in step size and produce an emergent force that breaks reparametrization symmetries while favoring minimum entropy production trajectories.