Abstract
The supervisor and searcher cooperation framework (SSC), introduced in Refs. 1 and 2, provides an effective way to design efficient optimization algorithms combining the desirable features of the two existing ones. This work aims to develop efficient algorithms for a wide range of noisy optimization problems including those posed by feedforward neural networks training. It introduces two basic SSC algorithms. The first seems suited for generic problems. The second is motivated by neural networks training problems. It introduces also inexact variants of the two algorithms, which seem to possess desirable properties. It establishes general theoretical results about the convergence and speed of SSC algorithms and illustrates their appealing attributes through numerical tests on deterministic, stochastic, and neural networks training problems.
Original language | English |
---|---|
Pages (from-to) | 325-340 |
Number of pages | 15 |
Journal | Journal of Optimization Theory and Applications |
Volume | 129 |
Issue number | 2 |
DOIs | |
Publication status | Published - May 2006 |
Keywords
- nonlinear programming
- stochastic programming
- noisy optimization
- neural networks training
- GRADIENT-METHOD
- BARZILAI