3 papers
stat.ML2026
There Will Be a Scientific Theory of Deep Learning
Jamie Simon, Daniel Kunin, Alexander Atanasov +11
In this paper, we make the case that a scientific theory of deep learning is emerging. By this we mean a theory which characterizes important properties and statistics of the train…
cs.LG2025
Predicting kernel regression learning curves from only raw data statistics
Dhruva Karkada, Joseph Turnbull, Yuxi Liu +1
We study kernel regression with common rotation-invariant kernels on real datasets including CIFAR-5m, SVHN, and ImageNet. We give a theoretical framework that predicts learning cu…
physics.bio-ph2024
Direct measure of DNA bending by quantum magnetic imaging of a nano-mechanical torque-balance
Zeeshawn Kazi, Isaac M. Shelby, Ruhee Nirodi +5
DNA flexibility is a key determinant of biological function, from nucleosome positioning to transcriptional regulation, motivating a direct measurement of the bend-torque response…