Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spacesby Anastasis Kratsios,…
Trade-Offs of Diagonal Fisher Information Matrix Estimatorsby Alexander Soen, Ke SunFirst submitted to arxiv on:…
Everybody Prune Now: Structured Pruning of LLMs with only Forward Passesby Lucio Dery, Steven Kolawole,…
Universal Neural Functionalsby Allan Zhou, Chelsea Finn, James HarrisonFirst submitted to arxiv on: 7 Feb…
AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Sizeby Petr Ostroukhov, Aigerim Zhumabayeva, Chulu Xiang,…
Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanesby Will Lavanakul, Jason J. Choi,…
Graph convolutional network as a fast statistical emulator for numerical ice sheet modelingby Maryam Rahnemoonfar,…
An information theoretic approach to quantify the stability of feature selection and ranking algorithmsby Alaiz-Rodriguez,…
Example-based Explanations for Random Forests using Machine Unlearningby Tanmay Surve, Romila PradhanFirst submitted to arxiv…
Strong convexity-guided hyper-parameter optimization for flatter lossesby Rahul Yedida, Snehanshu SahaFirst submitted to arxiv on:…