paper-with-me

Papers

RES: Regularized Stochastic BFGS Algorithm

2014-01-29 · Aryan Mokhtari, Alejandro Ribeiro

RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method is proposed to solve convex optimization problems with stochastic objectives. The use of stochastic gradient descent algorithms is widespread, but the number of iterations required to approximate optimal arguments can be prohibitive in high dimensional problems. Application of second order methods, on the other hand, is impracticable because computation of objective function Hessian inverses incurs excessive computational cost. BFGS modifies gradient descent by introducing a Hessian approximation matrix computed from finite gradient differences. RES utilizes stochastic gradients in lieu of deterministic gradients for both, the determination of descent directions and the approximation of the objective function's curvature. Since stochastic gradients can be computed at manageable computational cost RES is realizable and retains the convergence rate advantages of its deterministic counterparts. Convergence results show that lower and upper bounds on the Hessian egeinvalues of the sample functions are sufficient to guarantee convergence to optimal arguments. Numerical experiments showcase reductions in convergence time relative to stochastic gradient descent algorithms and non-regularized stochastic versions of BFGS. An application of RES to the implementation of support vector machines is developed.

📄 PDF Abstract BibTeX arXiv:1401.7625

Code (0)

등록된 구현이 없습니다.

Tasks

Second-order methods

Similar Papers 제목 키워드 기반

Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation

2019-10-11 · Si Yi Meng, Sharan Vaswani, Issam Laradji, Mark Schmidt 외

We consider stochastic second-order methods for minimizing smooth and strongly-convex functions under an interpolation condition satisfied by over-parameterized models. Under this condition, we show that the regularized …

Binary ClassificationSecond-order methods

mL-BFGS: A Momentum-based L-BFGS for Distributed Large-Scale Neural Network Optimization

2023-07-25 · Yue Niu, Zalan Fabian, Sunwoo Lee, Mahdi Soltanolkotabi 외

Quasi-Newton methods still face significant challenges in training large-scale neural networks due to additional compute costs in the Hessian related computations and instability issues in stochastic training. A well-kno…

Stochastic Optimization

Stochastic Damped L-BFGS with Controlled Norm of the Hessian Approximation

2020-12-10 · Sanae Lotfi, Tiphaine Bonniot de Ruisselet, Dominique Orban, Andrea Lodi

We propose a new stochastic variance-reduced damped L-BFGS algorithm, where we leverage estimates of bounds on the largest and smallest eigenvalues of the Hessian approximation to balance its quality and conditioning. Ou…

regression

Stochastic L-BFGS: Improved Convergence Rates and Practical Acceleration Strategies

2017-04-01 · Renbo Zhao, William B. Haskell, Vincent Y. F. Tan

We revisit the stochastic limited-memory BFGS (L-BFGS) algorithm. By proposing a new framework for the convergence analysis, we prove improved convergence rates and computational complexities of the stochastic L-BFGS alg…

regression

Implementation of Stochastic Quasi-Newton's Method in PyTorch

2018-05-07 · Yingkai Li, Huidong Liu

In this paper, we implement the Stochastic Damped LBFGS (SdLBFGS) for stochastic non-convex optimization. We make two important modifications to the original SdLBFGS algorithm. First, by initializing the Hessian at each …