6 citations · 7 across the 2 of their papers we have counts for
7 papers
Adaptive Sampling Quasi-Newton Methods for Zeroth-Order Stochastic Optimization
Raghu Bollapragada, Stefan M. Wild
We consider unconstrained stochastic optimization problems with no available gradient information. Such problems arise in settings from derivative-free simulation optimization to r…
Constrained and Composite Optimization via Adaptive Sampling Methods
Yuchen Xie, Raghu Bollapragada, Richard Byrd +1
The motivation for this paper stems from the desire to develop an adaptive sampling method for solving constrained optimization problems in which the objective function is stochast…
Optimization and Supervised Machine Learning Methods for Fitting Numerical Physics Models without Derivatives
Raghu Bollapragada, Matt Menickelly, Witold Nazarewicz +3
We address the calibration of a computationally expensive nuclear physics model for which derivative information with respect to the fit parameters is not readily available. Of par…
Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization
Raghu Bollapragada, Stefan M. Wild
We consider stochastic zero-order optimization problems, which arise in settings from simulation optimization to reinforcement learning. We propose an adaptive sampling quasi-Newto…
Nonlinear Acceleration of Momentum and Primal-Dual Algorithms
Raghu Bollapragada, Damien Scieur, Alexandre d'Aspremont
We describe convergence acceleration schemes for multistep optimization algorithms. The extrapolated solution is written as a nonlinear average of the iterates produced by the orig…
A Progressive Batching L-BFGS Method for Machine Learning
Raghu Bollapragada, Dheevatsa Mudigere, Jorge Nocedal +2
The standard L-BFGS method relies on gradient approximations that are not dominated by noise, so that search directions are descent directions, the line search is reliable, and qua…