Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation

• URL: http://arxiv.org/abs/2411.02001v1
• Date: Mon, 04 Nov 2024 11:38:27 GMT
• Title: Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
• Authors: Satoki Ishikawa, Rio Yokota, Ryo Karakida,
• Abstract summary: We introduce the maximal update parameterization ($mu$P) in the infinite-width limit for two representative designs of local targets. By analyzing deep linear networks, we found that PC's gradients interpolate between first-order and Gauss-Newton-like gradients. We demonstrate that, in specific standard settings, PC in the infinite-width limit behaves more similarly to the first-order gradient.
• Score: 8.35644084613785
• License:
• Abstract: Local learning, which trains a network through layer-wise local targets and losses, has been studied as an alternative to backpropagation (BP) in neural computation. However, its algorithms often become more complex or require additional hyperparameters because of the locality, making it challenging to identify desirable settings in which the algorithm progresses in a stable manner. To provide theoretical and quantitative insights, we introduce the maximal update parameterization ($\mu$P) in the infinite-width limit for two representative designs of local targets: predictive coding (PC) and target propagation (TP). We verified that $\mu$P enables hyperparameter transfer across models of different widths. Furthermore, our analysis revealed unique and intriguing properties of $\mu$P that are not present in conventional BP. By analyzing deep linear networks, we found that PC's gradients interpolate between first-order and Gauss-Newton-like gradients, depending on the parameterization. We demonstrate that, in specific standard settings, PC in the infinite-width limit behaves more similarly to the first-order gradient. For TP, even with the standard scaling of the last layer, which differs from classical $\mu$P, its local loss optimization favors the feature learning regime over the kernel regime.

Related papers

• LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layers [0.0468732641979009]
  We propose a layer-wise parameterization for convolutional neural networks (CNNs) that includes built-in robustness guarantees. Our method Lip Kernel directly parameterizes dissipative convolution kernels using a 2-D Roesser-type state space model. We show that the run-time using our method is orders of magnitude faster than state-of-the-art Lipschitz-bounded networks.
  arXiv  Detail & Related papers  (2024-10-29T17:20:14Z)
• RoPINN: Region Optimized Physics-Informed Neural Networks [66.38369833561039]
  Physics-informed neural networks (PINNs) have been widely applied to solve partial differential equations (PDEs) This paper proposes and theoretically studies a new training paradigm as region optimization. A practical training algorithm, Region Optimized PINN (RoPINN), is seamlessly derived from this new paradigm.
  arXiv  Detail & Related papers  (2024-05-23T09:45:57Z)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• Understanding the training of infinitely deep and wide ResNets with Conditional Optimal Transport [26.47265060394168]
  We show that the gradient flow for deep neural networks converges arbitrarily at a distance ofr. This is done by relying on the theory of gradient distance of finite width in spaces.
  arXiv  Detail & Related papers  (2024-03-19T16:34:31Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks [21.69222364939501]
  In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent from zero. We show that the path interpolates continuously between the so-called kernel and rich regimes.
  arXiv  Detail & Related papers  (2023-03-31T05:32:11Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• Training Sparse Neural Network by Constraining Synaptic Weight on Unit Lp Sphere [2.429910016019183]
  constraining the synaptic weights on unit Lp-sphere enables the flexibly control of the sparsity with p. Our approach is validated by experiments on benchmark datasets covering a wide range of domains.
  arXiv  Detail & Related papers  (2021-03-30T01:02:31Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)
• Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography [0.4110409960377149]
  We propose a novel convolutional neural network (CNN) designed for learning pseudodifferential operators ($Psi$DOs) in the context of linear inverse problems. We show that, under rather general assumptions on the forward operator, the unfolded iterations of ISTA can be interpreted as the successive layers of a CNN. In particular, we prove that, in the case of LA-CT, the operations of upscaling, downscaling and convolution, can be exactly determined by combining the convolutional nature of the limited angle X-ray transform and basic properties defining a wavelet system.
  arXiv  Detail & Related papers  (2020-06-02T14:03:41Z)

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.