NERDS LAB

  • About
  • Research
    • Papers
    • Code / Data
  • People
    • Lab Members
    • PI-Profile
  • News
  • Contact Us

ICML 2024: Unveiling class disparities with spectral imbalance

July 9, 2024 by Eva Dyer

Chiraag will travel to Vienna this month to present two papers!

Check out the work here:

  • C. Kaushik+, R. Liu+, C-H Lin, A. Khera, M.Y. Jin, W. Ma, V. Muthukumar, E.L. Dyer: Balanced data, imbalanced spectra: Unveiling class disparities with spectral imbalance, to appear at ICML 2024 (+co-first authors)
  • C-H Lin, C. Kaushik, E.L. Dyer+ & V. Muthukumar+: The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective, Journal of Machine Learning Research (JMLR), (Code, Poster) (+ co-last authors)

Related

Filed Under: Posts

Recent Posts

  • NeurIPS 2024: Revealing connections between contrastive learning and optimal transport January 1, 2025
  • ICML 2024: Unveiling class disparities with spectral imbalance July 9, 2024
  • ICLR 2024: New work on data-adaptive position embeddings for timeseries transformers June 3, 2024
  • Check out this new visualization tool for behavior modeling! May 9, 2024
  • New paper on the theory of data augmentation in JMLR! April 8, 2024
  • New paper on data-adaptive latent augmentation to appear at WACV! January 6, 2024
IMG_2521
  • About
  • Research
  • People
  • News
  • Contact Us

Copyright © 2025 · Minimum Pro on Genesis Framework · WordPress · Log in