2 papers
cs.LG2020
Fast-Rate Loss Bounds via Conditional Information Measures with Applications to Neural Networks
Fredrik Hellström, Giuseppe Durisi
We present a framework to derive bounds on the test loss of randomized learning algorithms for the case of bounded loss functions. Drawing from Steinke & Zakynthinou (2020), this f…
astro-ph.CO2018
New constraints on inelastic dark matter from IceCube
Riccardo Catena, Fredrik Hellström
We study the capture and subsequent annihilation of inelastic dark matter (DM) in the Sun, placing constraints on the DM-nucleon scattering cross section from the null result of th…