2 papers
cs.LG2026
Neural network optimization strategies and the topography of the loss landscape
Jianneng Yu, Alexandre V. Morozov
Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter…
physics.data-an2023
An adaptive Bayesian approach to gradient-free global optimization
Jianneng Yu, Alexandre V. Morozov
Many problems in science and technology require finding global minima or maxima of various objective functions. The functions are typically high-dimensional; each function evaluati…