SFF smooths the non-convex loss landscape of pre-trained LTSMs by linear weight interpolation with a random model, enabling more effective fine-tuning while preserving pre-trained knowledge.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?
SFF smooths the non-convex loss landscape of pre-trained LTSMs by linear weight interpolation with a random model, enabling more effective fine-tuning while preserving pre-trained knowledge.