Time to Spectrum
"Time to Spectrum" research explores how analyzing the spectral properties of data – essentially, the distribution of its frequencies or eigenvalues – can improve various machine learning tasks. Current efforts focus on leveraging spectral information to enhance model training efficiency (e.g., through targeted training or dimensionality reduction), improve model explainability, and evaluate dataset quality for time series and other complex data. This approach holds significant promise for advancing diverse fields, from improving the performance and resource efficiency of large language models to enhancing medical image diagnostics and accelerating scientific simulations.
28papers
Papers - Page 2
March 26, 2024
January 18, 2024
November 15, 2022
April 12, 2022
February 8, 2022
January 1, 2022
December 14, 2021