Text

Generalized Momentum-Based Methods : A Hamiltonian Perspective

We take a Hamiltonian-based perspective to generalize Nesterov's accelerated gradient descent and Polyak's heavy ball method to a broad class of momentum methods in the setting of (possibly) constrained minimization in Euclidean and non-Euclidean normed vector spaces. Our perspective leads to a generic and unifying nonasymptotic analysis of convergence of these methods in both the function value (in the setting of convex optimization) and in the norm of the gradient (in the setting of unconstrained, possibly nonconvex, optimization). Our approach relies upon a time-varying Hamiltonian that produces generalized momentum methods as its equations of motion. The convergence analysis for these methods is intuitive and is based on the conserved quantities of the time-dependent Hamiltonian.


Read More: https://epubs.siam.org/doi/abs/10.1137/20M1322716

Ketersediaan

Informasi Detail

Judul Seri

SIAM JOURNAL ON OPTIMIZATION; Vol.31 No.1 January-March 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 915 - 944

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

ACCELERATION
STATIONARY POINTS
MOMENTUM-BASED METHODS
HAMILTONIAN DYNAMICS

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Jelena Diakonikolas, Michael I. Jordan

Versi lain/terkait

Lampiran Berkas

Komentar