Abstract
We introduce the regularized Newton method (rnm) for unconstrained convex optimization. For any convex function, with a bounded optimal set, the rnm generates a sequence that converges to the optimal set from any starting point. Moreover the rnm requires neither strong convexity nor smoothness properties in the entire space. If the function is strongly convex and smooth enough in the neighborhood of the solution then the rnm sequence converges to the unique solution with asymptotic quadratic rate. We characterized the neighborhood of the solution where the quadratic rate occurs.
Similar content being viewed by others
References
Ermoliev Y.M. (1966). Methods for solving nonlinear extremal problems (in Russian). Kibernetika 4: 1–17
Kantorovich L.V. (1948). Functional analysis and applied mathematics (in Russian). Uspekhi Mat. Nauk 3: 89–185
Levenberg K. (1944). A method for the solution of certain nonlinear problems in least squares. Q. Appl. Math. 2: 164–168
Marquardt D. (1963). An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math. 11: 431–441
Nesterov Y. and Nemirovsky A. (1994). Interior Point Polynomial Algorithms in Convex Programming. SIAM, Philadelphia
Nesterov, Y., Polyak, B.T.: Cubic Regularization of Newton Method and its Global Performance. Mathematical Programming. DOI 10.1007/s 10107-006-0706-8, published online 04/25/06
Polyak B.T. (1963). Gradient methods for the minimization of functionals. USSR Comp. Math. and Math. Phys. 3(4): 643–653
Polyak B.T. (1967). A general method of solving extremum problems. Sov. Math. Dokl. 3: 593–597
Polyak B.T. (1987). Introduction to Optimization. Optimization Software, New York
Shor N.Z. (1998). Nondifferentiable Optimization and Polynomial Problems. Kluwer, Boston
Smale S. (1986). Newton’s method estimates from data at one point. In: Ewing, R.E., Gross, K.I. and Martin, C.F. (eds) The Merging of Disciplines: New Directions in Pure, Applied, and Computational Mathematics, pp 185–196. Springer, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Polyak, R.A. Regularized Newton method for unconstrained convex optimization. Math. Program. 120, 125–145 (2009). https://doi.org/10.1007/s10107-007-0143-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-007-0143-3