Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.
World Scientific Publishing Company
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
support 1representative citing papers
A new ensemble for connected solutions in CSPs reveals a stable cluster of delocalized solutions in the symmetric binary perceptron up to a critical threshold κ_no-mem_loc.stab. that conventional approaches miss.
citing papers explorer
-
Continuous Limits of Coupled Flows in Representation Learning
Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.
-
Finding the right path: statistical mechanics of connected solutions in constraint satisfaction problems
A new ensemble for connected solutions in CSPs reveals a stable cluster of delocalized solutions in the symmetric binary perceptron up to a critical threshold κ_no-mem_loc.stab. that conventional approaches miss.