Deep Kernel Posterior Learning under Infinite Variance Prior Weights

• URL: http://arxiv.org/abs/2410.01284v1
• Date: Wed, 2 Oct 2024 07:13:17 GMT
• Title: Deep Kernel Posterior Learning under Infinite Variance Prior Weights
• Authors: Jorge Loría, Anindya Bhadra,
• Abstract summary: We show that a Bayesian deep neural network converges to a process with $alpha$-stable marginals in each layer that has a conditionally Gaussian representation. We also provide useful generalizations of the results of Lor'ia & Bhadra (2024) on shallow networks on shallow multi-layer networks. The computational and statistical benefits over competing approaches stand out in simulations and in demonstrations on benchmark data sets.
• Score: 1.5960546024967326
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neal (1996) proved that infinitely wide shallow Bayesian neural networks (BNN) converge to Gaussian processes (GP), when the network weights have bounded prior variance. Cho & Saul (2009) provided a useful recursive formula for deep kernel processes for relating the covariance kernel of each layer to the layer immediately below. Moreover, they worked out the form of the layer-wise covariance kernel in an explicit manner for several common activation functions. Recent works, including Aitchison et al. (2021), have highlighted that the covariance kernels obtained in this manner are deterministic and hence, precludes any possibility of representation learning, which amounts to learning a non-degenerate posterior of a random kernel given the data. To address this, they propose adding artificial noise to the kernel to retain stochasticity, and develop deep kernel inverse Wishart processes. Nonetheless, this artificial noise injection could be critiqued in that it would not naturally emerge in a classic BNN architecture under an infinite-width limit. To address this, we show that a Bayesian deep neural network, where each layer width approaches infinity, and all network weights are elliptically distributed with infinite variance, converges to a process with $\alpha$-stable marginals in each layer that has a conditionally Gaussian representation. These conditional random covariance kernels could be recursively linked in the manner of Cho & Saul (2009), even though marginally the process exhibits stable behavior, and hence covariances are not even necessarily defined. We also provide useful generalizations of the recent results of Lor\'ia & Bhadra (2024) on shallow networks to multi-layer networks, and remedy the computational burden of their approach. The computational and statistical benefits over competing approaches stand out in simulations and in demonstrations on benchmark data sets.

Related papers

• Random ReLU Neural Networks as Non-Gaussian Processes [20.607307985674428]
  We show that random neural networks with rectified linear unit activation functions are well-defined non-Gaussian processes. As a by-product, we demonstrate that these networks are solutions to differential equations driven by impulsive white noise.
  arXiv  Detail & Related papers  (2024-05-16T16:28:11Z)
• Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models [16.07760622196666]
  We study the deep equilibrium model (DEQ), an infinite-depth neural network with shared weight matrices across layers. Our analysis reveals that as the width of DEQ layers approaches infinity, it converges to a Gaussian process. Remarkably, this convergence holds even when the limits of depth and width are interchanged.
  arXiv  Detail & Related papers  (2023-10-16T19:00:43Z)
• Neural signature kernels as infinite-width-depth-limits of controlled ResNets [5.306881553301636]
  We consider randomly controlled ResNets defined as Euler-discretizations of neural controlled differential equations (Neural CDEs) We show that in the infinite-width-depth limit and under proper scaling, these architectures converge weakly to Gaussian processes indexed on some spaces of continuous paths. We show that in the infinite-depth regime, finite-width controlled ResNets converge in distribution to Neural CDEs with random vector fields.
  arXiv  Detail & Related papers  (2023-03-30T19:20:16Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK [86.45209429863858]
  We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime. We show that the neural networks possess a different limiting kernel which we call textitbias-generalized NTK We also study various properties of the neural networks with this new kernel.
  arXiv  Detail & Related papers  (2023-01-01T02:11:39Z)
• On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks [91.3755431537592]
  We study how random pruning of the weights affects a neural network's neural kernel (NTK) In particular, this work establishes an equivalence of the NTKs between a fully-connected neural network and its randomly pruned version.
  arXiv  Detail & Related papers  (2022-03-27T15:22:19Z)
• The Separation Capacity of Random Neural Networks [78.25060223808936]
  We show that a sufficiently large two-layer ReLU-network with standard Gaussian weights and uniformly distributed biases can solve this problem with high probability. We quantify the relevant structure of the data in terms of a novel notion of mutual complexity.
  arXiv  Detail & Related papers  (2021-07-31T10:25:26Z)
• Redundant representations help generalization in wide neural networks [71.38860635025907]
  We study the last hidden layer representations of various state-of-the-art convolutional neural networks. We find that if the last hidden representation is wide enough, its neurons tend to split into groups that carry identical information, and differ from each other only by statistically independent noise.
  arXiv  Detail & Related papers  (2021-06-07T10:18:54Z)
• Large-width functional asymptotics for deep Gaussian neural networks [2.7561479348365734]
  We consider fully connected feed-forward deep neural networks where weights and biases are independent and identically distributed according to Gaussian distributions. Our results contribute to recent theoretical studies on the interplay between infinitely wide deep neural networks and processes.
  arXiv  Detail & Related papers  (2021-02-20T10:14:37Z)
• Finite Versus Infinite Neural Networks: an Empirical Study [69.07049353209463]
  kernel methods outperform fully-connected finite-width networks. Centered and ensembled finite networks have reduced posterior variance. Weight decay and the use of a large learning rate break the correspondence between finite and infinite networks.
  arXiv  Detail & Related papers  (2020-07-31T01:57:47Z)
• Stable behaviour of infinitely wide deep neural networks [8.000374471991247]
  We consider fully connected feed-forward deep neural networks (NNs) where weights and biases are independent and identically distributed. We show that the infinite wide limit of the NN, under suitable scaling on the weights, is a process whose finite-dimensional distributions are stable distributions.
  arXiv  Detail & Related papers  (2020-03-01T04:07:30Z)

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.