An official website of the United States government
Abstract In this paper, we explore the non-asymptotic global convergence rates of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method implemented with exact line search. Notably, due to Dixon’s equivalence result, our findings are also applicable to other quasi-Newton methods in the convex Broyden class employing exact line search, such as the Davidon-Fletcher-Powell (DFP) method. Specifically, we focus on problems where the objective function is strongly convex with Lipschitz continuous gradient and Hessian. Our results hold for any initial point and any symmetric positive definite initial Hessian approximation matrix. The analysis unveils a detailed three-phase convergence process, characterized by distinct linear and superlinear rates, contingent on the iteration progress. Additionally, our theoretical findings demonstrate the trade-offs between linear and superlinear convergence rates for BFGS when we modify the initial Hessian approximation matrix, a phenomenon further corroborated by our numerical experiments.
more »
« less
On the Derivation of Quasi-Newton Formulas for Optimization in Function Spaces
Newton's method is usually preferred when solving optimization problems due to its superior convergence properties compared to gradient-based or derivative-free optimization algorithms. However, deriving and computing second-order derivatives needed by Newton's method often is not trivial and, in some cases, not possible. In such cases quasi-Newton algorithms are a great alternative. In this paper, we provide a new derivation of well-known quasi-Newton formulas in an infinite-dimensional Hilbert space setting. It is known that quasi-Newton update formulas are solutions to certain variational problems over the space of symmetric matrices. In this paper, we formulate similar variational problems over the space of bounded symmetric operators in Hilbert spaces. By changing the constraints of the variational problem we obtain updates (for the Hessian and Hessian inverse) not only for the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method but also for Davidon--Fletcher--Powell (DFP), Symmetric Rank One (SR1), and Powell-Symmetric-Broyden (PSB). In addition, for an inverse problem governed by a partial differential equation (PDE), we derive DFP and BFGS ``structured" secant formulas that explicitly use the derivative of the regularization and only approximates the second derivative of the misfit term. We show numerical results that demonstrate the desired mesh-independence property and superior performance of the resulting quasi-Newton methods.
more »
« less
- Award ID(s):
- 1654311
- PAR ID:
- 10184514
- Date Published:
- Journal Name:
- Numerical Functional Analysis and Optimization
- Volume:
- 41
- Issue:
- 13
- ISSN:
- 0163-0563
- Page Range / eLocation ID:
- 1564–1587
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract In this paper, we study and prove the non-asymptotic superlinear convergence rate of the Broyden class of quasi-Newton algorithms which includes the Davidon–Fletcher–Powell (DFP) method and the Broyden–Fletcher–Goldfarb–Shanno (BFGS) method. The asymptotic superlinear convergence rate of these quasi-Newton methods has been extensively studied in the literature, but their explicit finite–time local convergence rate is not fully investigated. In this paper, we provide a finite–time (non-asymptotic) convergence analysis for Broyden quasi-Newton algorithms under the assumptions that the objective function is strongly convex, its gradient is Lipschitz continuous, and its Hessian is Lipschitz continuous at the optimal solution. We show that in a local neighborhood of the optimal solution, the iterates generated by both DFP and BFGS converge to the optimal solution at a superlinear rate of$$(1/k)^{k/2}$$ , wherekis the number of iterations. We also prove a similar local superlinear convergence result holds for the case that the objective function is self-concordant. Numerical experiments on several datasets confirm our explicit convergence rate bounds. Our theoretical guarantee is one of the first results that provide a non-asymptotic superlinear convergence rate for quasi-Newton methods.more » « less
-
Many machine learning problems optimize an objective that must be measured with noise. The primary method is a first order stochastic gradient descent using one or more Monte Carlo (MC) samples at each step. There are settings where ill-conditioning makes second order methods such as limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) more effective. We study the use of randomized quasi-Monte Carlo (RQMC) sampling for such problems. When MC sampling has a root mean squared error (RMSE) of O(n−1/2) then RQMC has an RMSE of o(n−1/2) that can be close to O(n−3/2) in favorable settings. We prove that improved sampling accuracy translates directly to improved optimization. In our empirical investigations for variational Bayes, using RQMC with stochastic quasi-Newton method greatly speeds up the optimization, and sometimes finds a better parameter value than MC does.more » « less
-
SUMMARY We present our third and final generation joint P and S global adjoint tomography (GLAD) model, GLAD-M35, and quantify its uncertainty based on a low-rank approximation of the inverse Hessian. Starting from our second-generation model, GLAD-M25, we added 680 new earthquakes to the database for a total of 2160 events. New P-wave categories are included to compensate for the imbalance between P- and S-wave measurements, and we enhanced the window selection algorithm to include more major-arc phases, providing better constraints on the structure of the deep mantle and more than doubling the number of measurement windows to 40 million. Two stages of a Broyden–Fletcher–Goldfarb–Shanno (BFGS) quasi-Newton inversion were performed, each comprising five iterations. With this BFGS update history, we determine the model’s standard deviation and resolution length through randomized singular value decomposition.more » « less
-
Al-Baali, Mehiddin; Purnama, Anton; Grandinetti, Lucio (Ed.)Second order, Newton-like algorithms exhibit convergence properties superior to gradient-based or derivative-free optimization algorithms. However, deriving and computing second order derivatives--needed for the Hessian-vector product in a Krylov iteration for the Newton step--often is not trivial. Second order adjoints provide a systematic and efficient tool to derive second derivative infor- mation. In this paper, we consider equality constrained optimization problems in an infinite-dimensional setting. We phrase the optimization problem in a general Banach space framework and derive second order sensitivities and second order adjoints in a rigorous and general way. We apply the developed framework to a partial differential equation-constrained optimization problem.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1080/01630563.2020.1785496
