Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Efficiently Verifiable Proofs of Data Attribution
Ari Karchmer, Martin Pawelczyk, Seth Neel
Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation o…
cs.LG2025
The Power of Random Features and the Limits of Distribution-Free Gradient Descent
Ari Karchmer, Eran Malach
We study the relationship between gradient-based optimization of parametric models (e.g., neural networks) and optimization of linear combinations of random features. Our main resu…