A spectral dictionary language model with learned sinusoidal atoms and a Gaussian mixture prior reports competitive validation perplexity at lower cost, but lacks test-set and code support.
K-svd: An algorithm for designing overcomplete dictionaries for sparse representation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
A spectral dictionary language model with learned sinusoidal atoms and a Gaussian mixture prior reports competitive validation perplexity at lower cost, but lacks test-set and code support.