Neural networks prioritize amplitude over phase in Fourier space during training on translation-invariant data; power-law spectra accelerate phase learning despite not aiding classification.
& Goldt, S.Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural NetworksinInternational Conference on Machine Learning235(PMLR, 2024), 3024–3045
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
Neural networks prioritize amplitude over phase in Fourier space during training on translation-invariant data; power-law spectra accelerate phase learning despite not aiding classification.