Derivation of Symmetric PCA Learning Rules from a Novel Objective Function

• URL: http://arxiv.org/abs/2005.11689v2
• Date: Thu, 28 May 2020 06:22:43 GMT
• Title: Derivation of Symmetric PCA Learning Rules from a Novel Objective Function
• Authors: Ralf M\"oller
• Abstract summary: Neural learning rules for principal component / subspace analysis can be derived by maximizing an objective function. For a subspace with a single axis, the optimization produces the principal eigenvector of the data covariance matrix. For a subspace with multiple axes, the optimization leads to PSA learning rules which only converge to axes spanning the principal subspace but not to the principal eigenvectors.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural learning rules for principal component / subspace analysis (PCA / PSA) can be derived by maximizing an objective function (summed variance of the projection on the subspace axes) under an orthonormality constraint. For a subspace with a single axis, the optimization produces the principal eigenvector of the data covariance matrix. Hierarchical learning rules with deflation procedures can then be used to extract multiple eigenvectors. However, for a subspace with multiple axes, the optimization leads to PSA learning rules which only converge to axes spanning the principal subspace but not to the principal eigenvectors. A modified objective function with distinct weight factors had to be introduced produce PCA learning rules. Optimization of the objective function for multiple axes leads to symmetric learning rules which do not require deflation procedures. For the PCA case, the estimated principal eigenvectors are ordered (w.r.t. the corresponding eigenvalues) depending on the order of the weight factors. Here we introduce an alternative objective function where it is not necessary to introduce fixed weight factors; instead, the alternative objective function uses squared summands. Optimization leads to symmetric PCA learning rules which converge to the principal eigenvectors, but without imposing an order. In place of the diagonal matrices with fixed weight factors, variable diagonal matrices appear in the learning rules. We analyze this alternative approach by determining the fixed points of the constrained optimization. The behavior of the constrained objective function at the fixed points is analyzed which confirms both the PCA behavior and the fact that no order is imposed. Different ways to derive learning rules from the optimization of the objective function are presented. The role of the terms in the learning rules obtained from these derivations is explored.

Related papers

• Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry [63.694184882697435]
  Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations.
  arXiv  Detail & Related papers  (2024-07-15T07:11:44Z)
• Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning [24.97120654216651]
  We show how to solve difficult differential equations with momentum on a submanifold. We do so by proposing a generalized version of the Riemannian normal coordinates. We use our approach to simplify existing approaches for structured covariances and develop matrix-inverse-free $2textnd$orders for deep learning with low precision by using only matrix multiplications.
  arXiv  Detail & Related papers  (2023-02-20T03:31:11Z)
• Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes [80.89852729380425]
  We propose the first computationally efficient algorithm that achieves the nearly minimax optimal regret $tilde O(dsqrtH3K)$. Our work provides a complete answer to optimal RL with linear MDPs, and the developed algorithm and theoretical tools may be of independent interest.
  arXiv  Detail & Related papers  (2022-12-12T18:58:59Z)
• Robust Geometric Metric Learning [17.855338784378]
  This paper proposes new algorithms for the metric learning problem. A general approach, called Robust Geometric Metric Learning (RGML), is then studied. The performance of RGML is asserted on real datasets.
  arXiv  Detail & Related papers  (2022-02-23T14:55:08Z)
• When Random Tensors meet Random Matrices [50.568841545067144]
  This paper studies asymmetric order-$d$ spiked tensor models with Gaussian noise. We show that the analysis of the considered model boils down to the analysis of an equivalent spiked symmetric textitblock-wise random matrix.
  arXiv  Detail & Related papers  (2021-12-23T04:05:01Z)
• Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation [71.27989298860481]
  We address the non- optimisation problem of finding a matrix on the Stiefel manifold that maximises a quadratic objective function. We propose a simple yet effective sparsity-promoting algorithm for finding the dominant eigenspace matrix.
  arXiv  Detail & Related papers  (2021-09-30T19:17:35Z)
• Jacobian Determinant of Normalizing Flows [7.124391555099448]
  Normalizing flows learn a diffeomorphic mapping between the target and base distribution. Jacobian determinant of that mapping forms another real-valued function. To stabilize normalizing flows training, it is required to maintain a balance between the expansiveness and contraction of volume.
  arXiv  Detail & Related papers  (2021-02-12T14:09:28Z)
• Unsupervised Ground Metric Learning using Wasserstein Eigenvectors [0.0]
  Key bottleneck is design of a "ground" cost which should be adapted to the task under study. In this paper, we propose for the first time a canonical answer by computing the ground cost as a positive eigenvector of the function mapping a cost to the pairwise OT distances between the inputs. We also introduce a scalable computational method using entropic regularization, which operates a principal component analysis dimensionality reduction.
  arXiv  Detail & Related papers  (2021-02-11T21:32:59Z)
• Improved Convergence Speed of Fully Symmetric Learning Rules for Principal Component Analysis [0.0]
  We describe a modified objective function with an additional term which mitigates this convergence problem. We show that the learning rule derived from the modified objective function inherits all fixed points from the original learning rule.
  arXiv  Detail & Related papers  (2020-07-18T13:41:35Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)
• Supervised Quantile Normalization for Low-rank Matrix Approximation [50.445371939523305]
  We learn the parameters of quantile normalization operators that can operate row-wise on the values of $X$ and/or of its factorization $UV$ to improve the quality of the low-rank representation of $X$ itself. We demonstrate the applicability of these techniques on synthetic and genomics datasets.
  arXiv  Detail & Related papers  (2020-02-08T21:06:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.