@tensorflow/tfjs-core/dist/ops/linalg/qr.d.ts

Hardware-accelerated JavaScript library for machine intelligence

/// <amd-module name="@tensorflow/tfjs-core/dist/ops/linalg/qr" />
import { Tensor } from '../../tensor';
/**
 * Compute QR decomposition of m-by-n matrix using Householder transformation.
 *
 * Implementation based on
 *   [http://www.cs.cornell.edu/~bindel/class/cs6210-f09/lec18.pdf]
 * (http://www.cs.cornell.edu/~bindel/class/cs6210-f09/lec18.pdf)
 *
 * ```js
 * const a = tf.tensor2d([[1, 2], [3, 4]]);
 * let [q, r] = tf.linalg.qr(a);
 * console.log('Q');
 * q.print();
 * console.log('R');
 * r.print();
 * console.log('Orthogonalized');
 * q.dot(q.transpose()).print()  // should be nearly the identity matrix.
 * console.log('Reconstructed');
 * q.dot(r).print(); // should be nearly [[1, 2], [3, 4]];
 * ```
 *
 * @param x The `tf.Tensor` to be QR-decomposed. Must have rank >= 2. Suppose
 *   it has the shape `[..., M, N]`.
 * @param fullMatrices An optional boolean parameter. Defaults to `false`.
 *   If `true`, compute full-sized `Q`. If `false` (the default),
 *   compute only the leading N columns of `Q` and `R`.
 * @returns An `Array` of two `tf.Tensor`s: `[Q, R]`. `Q` is a unitary matrix,
 *   i.e., its columns all have unit norm and are mutually orthogonal.
 *   If `M >= N`,
 *     If `fullMatrices` is `false` (default),
 *       - `Q` has a shape of `[..., M, N]`,
 *       - `R` has a shape of `[..., N, N]`.
 *     If `fullMatrices` is `true` (default),
 *       - `Q` has a shape of `[..., M, M]`,
 *       - `R` has a shape of `[..., M, N]`.
 *   If `M < N`,
 *     - `Q` has a shape of `[..., M, M]`,
 *     - `R` has a shape of `[..., M, N]`.
 * @throws If the rank of `x` is less than 2.
 *
 * @doc {heading:'Operations',
 *       subheading:'Linear Algebra',
 *       namespace:'linalg'}
 */
declare function qr_(x: Tensor, fullMatrices?: boolean): [Tensor, Tensor];
export declare const qr: typeof qr_;
export {};