Search Results for author:
Found 4 papers, 2 papers with code
Exact Gauss-Newton Optimization for Training Deep Neural Networks
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.
Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks
This work studies a GGN method for optimizing a two-layer neural network with explicit regularization.
Self-concordant Smoothing for Large-Scale Convex Composite Optimization
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.
SCORE: Approximating Curvature Information under Self-Concordant Regularization
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.
