| 来源类型 | Working Paper |
| 规范类型 | 报告 |
| DOI | 10.3386/t0317 |
| 来源ID | Technical Working Paper 0317 |
| Generalized Stochastic Gradient Learning | |
| George W. Evans; Seppo Honkapohja; Noah Williams | |
| 发表日期 | 2005-10-17 |
| 出版年 | 2005 |
| 语种 | 英语 |
| 摘要 | We study the properties of generalized stochastic gradient (GSG) learning in forward-looking models. We examine how the conditions for stability of standard stochastic gradient (SG) learning both differ from and are related to E-stability, which governs stability under least squares learning. SG algorithms are sensitive to units of measurement and we show that there is a transformation of variables for which E-stability governs SG stability. GSG algorithms with constant gain have a deeper justification in terms of parameter drift, robustness and risk sensitivity. |
| 主题 | Microeconomics ; Mathematical Tools ; Economics of Information ; Macroeconomics ; Macroeconomic Models |
| URL | https://www.nber.org/papers/t0317 |
| 来源智库 | National Bureau of Economic Research (United States) |
| 引用统计 | |
| 资源类型 | 智库出版物 |
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/569341 |
| 推荐引用方式 GB/T 7714 | George W. Evans,Seppo Honkapohja,Noah Williams. Generalized Stochastic Gradient Learning. 2005. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 资源类型 | 版本类型 | 开放类型 | 使用许可 | ||
| t0317.pdf（352KB） | 智库出版物 | 限制开放 | CC BY-NC-SA | 浏览 | ||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
