# MultivariateLinearRegressor A multivariate linear regressor. ``` struct MultivariateLinearRegressor where Scalar : MLShapedArrayScalar, Scalar : BinaryFloatingPoint ``` ## Overview Unlike a [`LinearRegressor`](/documentation/CreateMLComponents/LinearRegressor), a [`MultivariateLinearRegressor`](/documentation/CreateMLComponents/MultivariateLinearRegressor) supports shaped array outputs with any number of elements. It also provides a wider range of training options better suited for large multi-dimensional regression. > Note: Only `Float` and `Double` are currently supported as the Scalar type. You may get faster training > when using `Float`. ## Topics ### Creating a regressor [`init(configuration: MultivariateLinearRegressor.Configuration)`](/documentation/CreateMLComponents/MultivariateLinearRegressor/init(configuration:)) Creates a multivariate linear regressor. ### Getting the configuration [`var configuration: MultivariateLinearRegressor.Configuration`](/documentation/CreateMLComponents/MultivariateLinearRegressor/configuration-swift.property) The linear regressor configuration. ### Fitting [`func fitted(to: some Sequence, MLShapedArray>>, eventHandler: EventHandler?) async throws -> MultivariateLinearRegressor.Model`](/documentation/CreateMLComponents/MultivariateLinearRegressor/fitted(to:eventHandler:)) Fits a linear regressor model to a sequence of annotated features. [`func fitted(to:validateOn:eventHandler:)`](/documentation/CreateMLComponents/MultivariateLinearRegressor/fitted(to:validateOn:eventHandler:)) Fits a linear regressor model to shaped arrays of features and annotations. ### Fitting Progressively [`func makeTransformer() -> MultivariateLinearRegressor.Model`](/documentation/CreateMLComponents/MultivariateLinearRegressor/makeTransformer()) Creates a default-initialized model suitable for incremental fitting. [`func update(inout MultivariateLinearRegressor.Model, with: some Sequence, MLShapedArray>>, eventHandler: EventHandler?) async throws`](/documentation/CreateMLComponents/MultivariateLinearRegressor/update(_:with:eventHandler:)) Updates a model with a new sequence of examples. [`func update(inout MultivariateLinearRegressor.Model, with: AnnotatedBatch) async throws -> Scalar`](/documentation/CreateMLComponents/MultivariateLinearRegressor/update(_:with:)) Updates a model with a new shaped array of examples. ### Encoding and decoding [`func encodeWithOptimizer(MultivariateLinearRegressor.Model, to: inout any EstimatorEncoder) throws`](/documentation/CreateMLComponents/MultivariateLinearRegressor/encodeWithOptimizer(_:to:)) Encodes the model and optimizer to an encoder. [`func decodeWithOptimizer(from: inout any EstimatorDecoder) throws -> MultivariateLinearRegressor.Model`](/documentation/CreateMLComponents/MultivariateLinearRegressor/decodeWithOptimizer(from:)) Reads the encoded model and optimizer with a decoder. ### Supporting types [`struct Model`](/documentation/CreateMLComponents/MultivariateLinearRegressor/Model) A trained multivariate linear regressor model. [`typealias Annotation`](/documentation/CreateMLComponents/MultivariateLinearRegressor/Annotation) The annotation type. [`typealias Configuration`](/documentation/CreateMLComponents/MultivariateLinearRegressor/Configuration-swift.typealias) [`typealias Feature`](/documentation/CreateMLComponents/MultivariateLinearRegressor/Feature) The feature type. [`typealias Transformer`](/documentation/CreateMLComponents/MultivariateLinearRegressor/Transformer) The transformer type created by this estimator. ### Default Implementations [UpdatableSupervisedEstimator Implementations](/documentation/CreateMLComponents/MultivariateLinearRegressor/UpdatableSupervisedEstimator-Implementations) ## Relationships ### Conforms To [`Sendable`](/documentation/Swift/Sendable) [`Escapable`](/documentation/Swift/Escapable) [`Copyable`](/documentation/Swift/Copyable) [`UpdatableSupervisedEstimator`](/documentation/CreateMLComponents/UpdatableSupervisedEstimator) [`SupervisedEstimator`](/documentation/CreateMLComponents/SupervisedEstimator) [`SendableMetatype`](/documentation/Swift/SendableMetatype) --- Copyright © 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)