Stopping Rules for Gradient Methods for Non-Convex Problems with Additive Noise in Gradient

Comput. Math. Math. Phys. 3

Polyak, B.T.: Gradient methods for minimizing functionals · 1963

Earlier work this paper cites.

Autom. Remote Control 39

Emelin, I.V., Krasnosel’skii, M.A.: The stoppage rule in iterative procedures of solving ill-posed problems · 1978

Earlier work this paper cites.

In: Numerical methods of mathematical programming, pp. 77–91. Moscow (1980)

Nesterov, Y., Skokov, V.: On the issue of testing unconstrained optimization algorithms · 1980

Earlier work this paper cites.

Inc., New York 1

Polyak, B.T.: Introduction to optimization. optimization software · 1987

Earlier work this paper cites.

Moscow: FP (2002)

Vasilyev, F.: Optimization methods · 2002

Earlier work this paper cites.

Mathematical Programming 108

Nesterov, Y., Polyak, B.T.: Cubic regularization of newton method and its global performance · 2006

Earlier work this paper cites.

SIAM Journal on Optimization 19

d’Aspremont, A.: Smooth optimization with approximate gradient · 2008

Cited alongside, same era.

In: Inverse and Ill-posed Problems. deGruyter (2011)

Kabanikhin, S.I.: Inverse and ill-posed problems · 2011

Cited alongside, same era.

Ph.D. thesis, ICTEAM and CORE, Université Catholique de Louvain (2013)

Devolder, O.: Exactness, inexactness and stochasticity in first-order methods for large-scale convex optimization · 2013

Cited alongside, same era.

Mathematical Programming 146

Devolder, O., Glineur, F., Nesterov, Y.: First-order methods of smooth convex optimization with inexact oracle · 2014

Cited alongside, same era.

Mathematical Programming 152

Nesterov, Y.: Universal gradient methods for convex optimization problems · 2015

Cited alongside, same era.

In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 795–811. Springer (2016)

Karimi, H., Nutini, J., Schmidt, M.: Linear convergence of gradient and proximal-gradient methods under the polyak-łojasiewicz condition · 2016

Optimization Methods and Software 35

Polyak, B., Tremba, A.: New versions of newton method: step-size choice, convergence domain and under-determined equations · 2020

Later among the works it cites.

Acta Numerica 30

Belkin, M.: Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation · 2021

Later among the works it cites.

(in Russian)

Gasnikov, A.V.: In: Modern Numerical Optimization Methods: The Universal Gradient Descent Method. Moscow, MCCME (2021) · 2021

Later among the works it cites.

arXiv preprint arXiv:2102.02921 (2021)

Original

Vasin, A., Gasnikov, A., Spokoiny, V.: Stopping rules for accelerated gradient methods with additive noise in gradient · 2021

Later among the works it cites.

(in Russian)

Vorontsova, E., Hildbrand, R., Gasnikov, A., Stonyakin, F.: Convex optimization (2021) · 2021

Later among the works it cites.