18 citations · 23 across the 8 of their papers we have counts for
3 papers · 1 filter
Decomposing multimodal embedding spaces with group-sparse autoencoders
Chiraag Kaushik, Davis Barch, Andrea Fanelli
The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concept…
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
Chiraag Kaushik, Ran Liu, Chi-Heng Lin +5
Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance. This issue of class bias is wide…
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer +1
Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning. Specific augmentations like translations and scaling in computer vision are tr…