On improving generalization in a class of learning problems with the method of small parameters for weakly-controlled optimal gradient systems

Shranjeno v:
Bibliografske podrobnosti
izdano v:arXiv.org (Dec 11, 2024), p. n/a
Glavni avtor: Befekadu, Getachew K
Izdano:
Cornell University Library, arXiv.org
Teme:
Online dostop:Citation/Abstract
Full text outside of ProQuest
Oznake: Označite
Brez oznak, prvi označite!

MARC

LEADER 00000nab a2200000uu 4500
001 3144199832
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3144199832 
045 0 |b d20241211 
100 1 |a Befekadu, Getachew K 
245 1 |a On improving generalization in a class of learning problems with the method of small parameters for weakly-controlled optimal gradient systems 
260 |b Cornell University Library, arXiv.org  |c Dec 11, 2024 
513 |a Working Paper 
520 3 |a In this paper, we provide a mathematical framework for improving generalization in a class of learning problems which is related to point estimations for modeling of high-dimensional nonlinear functions. In particular, we consider a variational problem for a weakly-controlled gradient system, whose control input enters into the system dynamics as a coefficient to a nonlinear term which is scaled by a small parameter. Here, the optimization problem consists of a cost functional, which is associated with how to gauge the quality of the estimated model parameters at a certain fixed final time w.r.t. the model validating dataset, while the weakly-controlled gradient system, whose the time-evolution is guided by the model training dataset and its perturbed version with small random noise. Using the perturbation theory, we provide results that will allow us to solve a sequence of optimization problems, i.e., a set of decomposed optimization problems, so as to aggregate the corresponding approximate optimal solutions that are reasonably sufficient for improving generalization in such a class of learning problems. Moreover, we also provide an estimate for the rate of convergence for such approximate optimal solutions. Finally, we present some numerical results for a typical case of nonlinear regression problem. 
653 |a System dynamics 
653 |a Datasets 
653 |a Random noise 
653 |a Parameter estimation 
653 |a Learning 
653 |a Nonlinear control 
653 |a Functions (mathematics) 
653 |a Perturbation theory 
653 |a Nonlinear dynamics 
653 |a Optimization 
653 |a Functionals 
773 0 |t arXiv.org  |g (Dec 11, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3144199832/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.08772