A frequency-domain analysis of inexact gradient methods

نویسندگان

چکیده

We study robustness properties of some iterative gradient-based methods for strongly convex functions, as well the larger class functions with sector-bounded gradients, under a relative error model. Proofs corresponding convergence rates are based on frequency-domain criteria stability nonlinear systems. Applications given to inexact versions gradient descent and Triple Momentum Method. To further emphasize usefulness methods, we derive improved analytic bounds rate Nesterov’s accelerated method (in exact setting) functions.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Frequency-Domain Harmonic Analysis Methods

There are a large number of frequency-domain analysis methods that are in widespread use. The most popular of these are frequency scans, harmonic penetration, and harmonic power flow. Each of these techniques can be employed on a “per-phase” (positive or zero sequence) or “multi-phase” basis and each technique utilizes an admittance matrix system model developed from individual component-level ...

متن کامل

Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization

We consider the problem of optimizing the sum of a smooth convex function and a non-smooth convex function using proximal-gradient methods, where an error is present in the calculation of the gradient of the smooth term or in the proximity operator with respect to the non-smooth term. We show that both the basic proximal-gradient method and the accelerated proximal-gradient method achieve the s...

متن کامل

Frequency-Domain Analysis of Spin Motion Using Modulated-Gradient NMR

In pulsed-gradient spin-echo NMR, one measures the disof rotational dipolar auto-correlation spectral density via the ‘‘probe’’ of the spin relaxation times, where T1 samples at placement of nuclear spins over the time interval, D, between two gradient pulses, of duration d and amplitude g , positions v0 and 2v0 , while T1r samples at v1 and 2v1 . The purpose of the present Communication is to ...

متن کامل

Intermediate Gradient Methods for Smooth Convex Problems with Inexact Oracle

Between the robust but slow (primal or dual) gradient methods and the fast but sensitive to errors fast gradient methods, our goal in this paper is to develop first-order methods for smooth convex problems with intermediate speed and intermediate sensitivity to errors. We develop a general family of first-order methods, the Intermediate Gradient Method (IGM), based on two sequences of coefficie...

متن کامل

Inexact Spectral Projected Gradient Methods on Convex Sets

A new method is introduced for large scale convex constrained optimization. The general model algorithm involves, at each iteration, the approximate minimization of a convex quadratic on the feasible set of the original problem and global convergence is obtained by means of nonmonotone line searches. A specific algorithm, the Inexact Spectral Projected Gradient method (ISPG), is implemented usi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Mathematical Programming

سال: 2021

ISSN: ['0025-5610', '1436-4646']

DOI: https://doi.org/10.1007/s10107-021-01665-8