<!--
{
  "availability" : [
    "iOS: 14.0.0 -",
    "iPadOS: 14.0.0 -",
    "macCatalyst: 14.0.0 -",
    "macOS: 11.0.0 -",
    "tvOS: 14.0.0 -",
    "visionOS: 1.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "MetalPerformanceShadersGraph",
  "identifier" : "/documentation/MetalPerformanceShadersGraph/MPSGraph/stochasticGradientDescent(learningRate:values:gradient:name:)",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Method",
  "symbol" : {
    "kind" : "Instance Method",
    "modules" : [
      "Metal Performance Shaders Graph",
      "MetalPerformanceShadersGraph"
    ],
    "preciseIdentifier" : "c:objc(cs)MPSGraph(im)stochasticGradientDescentWithLearningRateTensor:valuesTensor:gradientTensor:name:"
  },
  "title" : "stochasticGradientDescent(learningRate:values:gradient:name:)"
}
-->

# stochasticGradientDescent(learningRate:values:gradient:name:)

The Stochastic gradient descent performs a gradient descent.

```
func stochasticGradientDescent(learningRate learningRateTensor: MPSGraphTensor, values valuesTensor: MPSGraphTensor, gradient gradientTensor: MPSGraphTensor, name: String?) -> MPSGraphTensor
```

## Parameters

`learningRateTensor`

scalar tensor which indicates the learning rate to use with the optimizer

`valuesTensor`

values tensor, usually representing the trainable parameters

`gradientTensor`

partial gradient of the trainable parameters with respect to loss

`name`

name for the operation

## Return Value

A valid MPSGraphTensor object.

## Discussion

`variable = variable - (learningRate * g)`
where,
`g` is gradient of error wrt variable

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)