J. Nocedal

activity

20132024

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

571 citations · 729 across the 15 of their papers we have counts for

collaborators

Showing 2014Show all

2 papers · 1 filter

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…

math.OC2014★ 43 cited

A Stochastic Quasi-Newton Method for Large-Scale Optimization

R. H. Byrd, S. L. Hansen, J. Nocedal +1

The question of how to incorporate curvature information in stochastic approximation methods is challenging. The direct application of classical quasi- Newton updating techniques f…

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

A Stochastic Quasi-Newton Method for Large-Scale Optimization

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