paper-with-me

홈 › Papers

Stochastic Quasi-Newton Optimization in Large Dimensions Including Deep Network Training

2024-10-18 · Uttam Suman, Mariya Mamajiwala, Mukul Saxena, Ankit Tyagi, Debasish Roy

Our proposal is on a new stochastic optimizer for non-convex and possibly non-smooth objective functions typically defined over large dimensional design spaces. Towards this, we have tried to bridge noise-assisted global search and faster local convergence, the latter being the characteristic feature of a Newton-like search. Our specific scheme -- acronymed FINDER (Filtering Informed Newton-like and Derivative-free Evolutionary Recursion), exploits the nonlinear stochastic filtering equations to arrive at a derivative-free update that has resemblance with the Newton search employing the inverse Hessian of the objective function. Following certain simplifications of the update to enable a linear scaling with dimension and a few other enhancements, we apply FINDER to a range of problems, starting with some IEEE benchmark objective functions to a couple of archetypal data-driven problems in deep networks to certain cases of physics-informed deep networks. The performance of the new method vis-\'a-vis the well-known Adam and a few others bears evidence to its promise and potentialities for large dimensional optimization problems of practical interest.

📄 PDF Abstract BibTeX arXiv:2410.14270

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization

2019-10-29 · 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-Newton method where we estimate the gradients…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Stochastic Optimization

Stochastic Newton and Quasi-Newton Methods for Large Linear Least-squares Problems

2017-02-23 · Julianne Chung, Matthias Chung, J. Tanner Slagel, Luis Tenorio

We describe stochastic Newton and stochastic quasi-Newton approaches to efficiently solve large linear least-squares problems where the very large data sets present a significant computational burden (e.g., the size may …

A Stochastic Extra-Step Quasi-Newton Method for Nonsmooth Nonconvex Optimization

2019-10-21 · Ming-Han Yang, Andre Milzarek, Zaiwen Wen, Tong Zhang

In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems. We assume that the gradient of the smooth part of the objective funct…

Deep Neural Network Learning with Second-Order Optimizers -- a Practical Study with a Stochastic Quasi-Gauss-Newton Method

2020-04-06 · Christopher Thiele, Mauricio Araya-Polo, Detlef Hohl

Training in supervised deep learning is computationally demanding, and the convergence behavior is usually not fully understood. We introduce and study a second-order stochastic quasi-Gauss-Newton (SQGN) optimization met…

Adaptive Sampling Quasi-Newton Methods for Zeroth-Order Stochastic Optimization

2021-09-24 · 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 reinforcement learning. We propose an ada…

Reinforcement Learning (RL)Stochastic Optimization