A Nondeterministic Minimization Algorithm
The problem of minimizing a multivariate function is recurrent in many disciplines as Physics, Mathematics, Engeneering and, of course, Computer Science. In this paper we describe a simple nondeterministic algorithm which is based on the idea of adaptive noise, and that proved to be particular...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6560 |
| _version_ | 1826193366526722048 |
|---|---|
| author | Caprile, Bruno Girosi, Federico |
| author_facet | Caprile, Bruno Girosi, Federico |
| author_sort | Caprile, Bruno |
| collection | MIT |
| description | The problem of minimizing a multivariate function is recurrent in many disciplines as Physics, Mathematics, Engeneering and, of course, Computer Science. In this paper we describe a simple nondeterministic algorithm which is based on the idea of adaptive noise, and that proved to be particularly effective in the minimization of a class of multivariate, continuous valued, smooth functions, associated with some recent extension of regularization theory by Poggio and Girosi (1990). Results obtained by using this method and a more traditional gradient descent technique are also compared. |
| first_indexed | 2024-09-23T09:38:15Z |
| id | mit-1721.1/6560 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:38:15Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/65602019-04-11T02:52:24Z A Nondeterministic Minimization Algorithm Caprile, Bruno Girosi, Federico The problem of minimizing a multivariate function is recurrent in many disciplines as Physics, Mathematics, Engeneering and, of course, Computer Science. In this paper we describe a simple nondeterministic algorithm which is based on the idea of adaptive noise, and that proved to be particularly effective in the minimization of a class of multivariate, continuous valued, smooth functions, associated with some recent extension of regularization theory by Poggio and Girosi (1990). Results obtained by using this method and a more traditional gradient descent technique are also compared. 2004-10-04T15:31:26Z 2004-10-04T15:31:26Z 1990-09-01 AIM-1254 http://hdl.handle.net/1721.1/6560 en_US AIM-1254 1240414 bytes 492517 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Caprile, Bruno Girosi, Federico A Nondeterministic Minimization Algorithm |
| title | A Nondeterministic Minimization Algorithm |
| title_full | A Nondeterministic Minimization Algorithm |
| title_fullStr | A Nondeterministic Minimization Algorithm |
| title_full_unstemmed | A Nondeterministic Minimization Algorithm |
| title_short | A Nondeterministic Minimization Algorithm |
| title_sort | nondeterministic minimization algorithm |
| url | http://hdl.handle.net/1721.1/6560 |
| work_keys_str_mv | AT caprilebruno anondeterministicminimizationalgorithm AT girosifederico anondeterministicminimizationalgorithm AT caprilebruno nondeterministicminimizationalgorithm AT girosifederico nondeterministicminimizationalgorithm |