Jorge Nocedal

most citedOn Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

571 citations · 571 across the 2 of their papers we have counts for

collaborators

Showing math.OCShow all

2 papers · 1 filter

math.OC2024

A Feasible Method for Constrained Derivative-Free Optimization

Melody Qiming Xuan, Jorge Nocedal

This paper explores a method for solving constrained optimization problems when the derivatives of the objective function are unavailable, while the derivatives of the constraints…

math.OC2014

An Algorithm for Quadratic $ℓ_{1}$ -Regularized Optimization with a Flexible Active-Set Strategy

Stefan Solntsev, Jorge Nocedal, Richard Byrd

We present an active-set method for minimizing an objective that is the sum of a convex quadratic and $ℓ_{1}$ regularization term. Unlike two-phase methods that combine a first-or…

A Feasible Method for Constrained Derivative-Free Optimization

An Algorithm for Quadratic ℓ1​-Regularized Optimization with a Flexible Active-Set Strategy

An Algorithm for Quadratic $ℓ_{1}$ -Regularized Optimization with a Flexible Active-Set Strategy