Gradient descent on randomly initialized matrix product states gets stuck in a causal trap that ignores boundary correlations, but natural gradient descent or a TTNS-Sketch warm start avoids the trap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Initialization and training of matrix product state probabilistic models
Gradient descent on randomly initialized matrix product states gets stuck in a causal trap that ignores boundary correlations, but natural gradient descent or a TTNS-Sketch warm start avoids the trap.