Under gradient and log-probability insensitivity assumptions, SGLD-based local learning coefficient estimates cannot distinguish a sequence distribution from its mode-truncated effective version.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Modes of Sequence Models and Learning Coefficients
Under gradient and log-probability insensitivity assumptions, SGLD-based local learning coefficient estimates cannot distinguish a sequence distribution from its mode-truncated effective version.