Annabelle Michael Carrell
@ab-carrell.bsky.social
PhD student in ML
If you’re not at ICML, you can still read our work. Our new theoretically principled algorithms beat recent baselines across multiple tasks—including Transformer approximation!
Low-Rank Thinning
The goal in thinning is to summarize a dataset using a small set of representative points. Remarkably, sub-Gaussian thinning algorithms like Kernel Halving and Compress can match the quality of unifor...
arxiv.org
July 14, 2025 at 6:29 PM
If you’re not at ICML, you can still read our work. Our new theoretically principled algorithms beat recent baselines across multiple tasks—including Transformer approximation!