| title | sgd_optimizer: sgd_optimizer |
|---|---|
| description | Stochastic gradient descent optimizer. |
| keywords | optimizer, sgd |
| author | WilliamDAssafMSFT |
| ms.author | wiassaf |
| manager | cgronlun |
| ms.date | 07/15/2019 |
| ms.topic | reference |
| ms.prod | sql |
| ms.technology | machine-learning-services |
| ms.service | |
| ms.assetid | |
| ROBOTS | |
| audience | |
| ms.devlang | Python |
| ms.reviewer | |
| ms.suite | |
| ms.tgt_pltfrm | |
| ms.custom | |
| monikerRange | >=sql-server-2017||>=sql-server-linux-ver15 |
microsoftml.sgd_optimizer(learning_rate: numbers.Real = None,
momentum: numbers.Real = None, nag: bool = None,
weight_decay: numbers.Real = None,
l_rate_red_ratio: numbers.Real = None,
l_rate_red_freq: numbers.Real = None,
l_rate_red_error_ratio: numbers.Real = None)
Stochastic gradient descent optimizer.
Learning rate (settings).
Momentum Term (settings).
Use Nesterov’s accelerated gradient (settings).
Weight decay (settings).
Learning rate reduction ratio (settings).
Learning rate reduction ratio (settings).
Relative error reduction criterion for learning rate reduction (settings).