Regularized linear autoencoders recover the principal components, eventually

• URL: http://arxiv.org/abs/2007.06731v2
• Date: Fri, 1 Oct 2021 17:42:49 GMT
• Title: Regularized linear autoencoders recover the principal components, eventually
• Authors: Xuchan Bao, James Lucas, Sushant Sachdeva, Roger Grosse
• Abstract summary: We show that when trained with proper regularization, linear autoencoders can learn the optimal representation. We show that this convergence is slow due to ill-conditioning that worsens with increasing latent dimension. We present a simple modification to the gradient descent update that greatly speeds up empirically.
• Score: 15.090789983727335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Our understanding of learning input-output relationships with neural nets has improved rapidly in recent years, but little is known about the convergence of the underlying representations, even in the simple case of linear autoencoders (LAEs). We show that when trained with proper regularization, LAEs can directly learn the optimal representation -- ordered, axis-aligned principal components. We analyze two such regularization schemes: non-uniform $\ell_2$ regularization and a deterministic variant of nested dropout [Rippel et al, ICML' 2014]. Though both regularization schemes converge to the optimal representation, we show that this convergence is slow due to ill-conditioning that worsens with increasing latent dimension. We show that the inefficiency of learning the optimal representation is not inevitable -- we present a simple modification to the gradient descent update that greatly speeds up convergence empirically.

Related papers

• Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization [52.16435732772263]
  Second-order optimization has been shown to accelerate the training of deep neural networks in many applications. However, generalization properties of second-order methods are still being debated. We show for the first time that exact Gauss-Newton (GN) updates take on a tractable form in a class of deep architectures.
  arXiv  Detail & Related papers  (2024-11-12T17:58:40Z)
• Implicit Bias and Fast Convergence Rates for Self-attention [30.08303212679308]
  Self-attention, the core mechanism of transformers, distinguishes them from traditional neural networks and drives their outstanding performance. We investigate the implicit bias of gradient descent (GD) in training a self-attention layer with fixed linear decoder in binary. We provide the first finite-time convergence rate for $W_t$ to $W_mm$, along with the rate of sparsification in the attention map.
  arXiv  Detail & Related papers  (2024-02-08T15:15:09Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm [101.44676036551537]
  One-way Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC) measures the average performance of a binary classifier. Most of the existing methods could only optimize PAUC approximately, leading to inevitable biases that are not controllable. We present a simpler reformulation of the PAUC problem via distributional robust optimization AUC.
  arXiv  Detail & Related papers  (2022-10-08T08:26:22Z)
• Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
  We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
  arXiv  Detail & Related papers  (2021-07-07T16:59:14Z)
• On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks [1.0323063834827415]
  We present a novel analysis of single-hidden-layer linear networks trained under gradient flow. We show that the squared loss converges exponentially to its optimum. We derive a novel non-asymptotic upper-bound on the distance between the trained network and the min-norm solution.
  arXiv  Detail & Related papers  (2021-05-13T15:13:51Z)
• Dissecting Supervised Constrastive Learning [24.984074794337157]
  Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. We show that one can directly optimize the encoder instead, to obtain equally (or even more) discriminative representations via a supervised variant of a contrastive objective.
  arXiv  Detail & Related papers  (2021-02-17T15:22:38Z)
• LQF: Linear Quadratic Fine-Tuning [114.3840147070712]
  We present the first method for linearizing a pre-trained model that achieves comparable performance to non-linear fine-tuning. LQF consists of simple modifications to the architecture, loss function and optimization typically used for classification.
  arXiv  Detail & Related papers  (2020-12-21T06:40:20Z)
• Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization [79.42778415729475]
  We explore an alternative solution based on explicit memorization using linear autoencoders for sequences. We show how such pretraining can better support solving hard classification tasks with long sequences. We show that the proposed approach achieves a much lower reconstruction error for long sequences and a better gradient propagation during the finetuning phase.
  arXiv  Detail & Related papers  (2020-11-05T14:57:16Z)
• Towards Understanding Label Smoothing [36.54164997035046]
  Label smoothing regularization (LSR) has a great success in deep neural networks by training algorithms. We show that an appropriate LSR can help to speed up convergence by reducing the variance. We propose a simple yet effective strategy, namely Two-Stage LAbel smoothing algorithm (TSLA)
  arXiv  Detail & Related papers  (2020-06-20T20:36:17Z)
• The Implicit Bias of Gradient Descent on Separable Data [44.98410310356165]
  We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. This can help explain the benefit of continuing to optimize the logistic or cross-entropy loss even after the training error is zero.
  arXiv  Detail & Related papers  (2017-10-27T21:47:58Z)

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.