no code implementations • 23 May 2024 • Mikalai Korbit, Adeyemi D. Adeoye, Alberto Bemporad, Mario Zanon
We present EGN, a stochastic second-order optimization algorithm that combines the generalized Gauss-Newton (GN) Hessian approximation with low-rank linear algebra to compute the descent direction.
1 code implementation • 23 Apr 2024 • Adeyemi D. Adeoye, Philipp Christian Petersen, Alberto Bemporad
This work studies a GGN method for optimizing a two-layer neural network with explicit regularization.
1 code implementation • 4 Sep 2023 • Adeyemi D. Adeoye, Alberto Bemporad
We introduce a notion of self-concordant smoothing for minimizing the sum of two convex functions, one of which is smooth and the other may be nonsmooth.
no code implementations • 14 Dec 2021 • Adeyemi D. Adeoye, Alberto Bemporad
In this paper, we propose the SCORE (self-concordant regularization) framework for unconstrained minimization problems which incorporates second-order information in the Newton-decrement framework for convex optimization.