Initializing sinusoidal time embeddings with FFT-extracted dominant frequencies and constraining their learning rate yields mixed improvements on traffic forecasting benchmarks, contradicting the paper's claim of consistent gains.
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
REJECT 1representative citing papers
citing papers explorer
-
Frequency-Constrained Learning for Long-Term Forecasting
Initializing sinusoidal time embeddings with FFT-extracted dominant frequencies and constraining their learning rate yields mixed improvements on traffic forecasting benchmarks, contradicting the paper's claim of consistent gains.