Scalable Neural Network Kernels

• URL: http://arxiv.org/abs/2310.13225v2
• Date: Tue, 5 Mar 2024 21:02:04 GMT
• Title: Scalable Neural Network Kernels
• Authors: Arijit Sehanobish, Krzysztof Choromanski, Yunfan Zhao, Avinava Dubey, Valerii Likhosherstov
• Abstract summary: We introduce scalable neural network kernels (SNNKs), capable of approximating regular feedforward layers (FFLs) We also introduce the neural network bundling process that applies SNNKs to compactify deep neural network architectures. Our mechanism provides up to 5x reduction in the number of trainable parameters, while maintaining competitive accuracy.
• Score: 22.299704296356836
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce the concept of scalable neural network kernels (SNNKs), the replacements of regular feedforward layers (FFLs), capable of approximating the latter, but with favorable computational properties. SNNKs effectively disentangle the inputs from the parameters of the neural network in the FFL, only to connect them in the final computation via the dot-product kernel. They are also strictly more expressive, as allowing to model complicated relationships beyond the functions of the dot-products of parameter-input vectors. We also introduce the neural network bundling process that applies SNNKs to compactify deep neural network architectures, resulting in additional compression gains. In its extreme version, it leads to the fully bundled network whose optimal parameters can be expressed via explicit formulae for several loss functions (e.g. mean squared error), opening a possibility to bypass backpropagation. As a by-product of our analysis, we introduce the mechanism of the universal random features (or URFs), applied to instantiate several SNNK variants, and interesting on its own in the context of scalable kernel methods. We provide rigorous theoretical analysis of all these concepts as well as an extensive empirical evaluation, ranging from point-wise kernel estimation to Transformers' fine-tuning with novel adapter layers inspired by SNNKs. Our mechanism provides up to 5x reduction in the number of trainable parameters, while maintaining competitive accuracy.

Related papers

• Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime [52.00917519626559]
  This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology. We also present an exact novel representor theory for layer-wise neural network training with unregularized gradient descent in terms of a local-extrinsic neural kernel (LeNK) This representor theory gives insight into the role of higher-order statistics in neural network training and the effect of kernel evolution in neural-network kernel models.
  arXiv  Detail & Related papers  (2024-05-24T06:30:36Z)
• Permutation Equivariant Neural Functionals [92.0667671999604]
  This work studies the design of neural networks that can process the weights or gradients of other neural networks. We focus on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. In our experiments, we find that permutation equivariant neural functionals are effective on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-02-27T18:52:38Z)
• Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning [23.47570704524471]
  We consider optimisation of large and shallow neural networks via gradient flow, where the output of each hidden node is scaled by some positive parameter. We prove that, for large neural networks, with high probability, gradient flow converges to a global minimum AND can learn features, unlike in the NTK regime.
  arXiv  Detail & Related papers  (2023-02-02T10:40:06Z)
• Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study [55.12108376616355]
  The study on NTK has been devoted to typical neural network architectures, but is incomplete for neural networks with Hadamard products (NNs-Hp) In this work, we derive the finite-width-K formulation for a special class of NNs-Hp, i.e., neural networks. We prove their equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK.
  arXiv  Detail & Related papers  (2022-09-16T06:36:06Z)
• Incorporating Prior Knowledge into Neural Networks through an Implicit Composite Kernel [1.6383321867266318]
  Implicit Composite Kernel (ICK) is a kernel that combines a kernel implicitly defined by a neural network with a second kernel function chosen to model known properties. We demonstrate ICK's superior performance and flexibility on both synthetic and real-world data sets.
  arXiv  Detail & Related papers  (2022-05-15T21:32:44Z)
• Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions [4.932130498861987]
  We propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions. Under suitable conditions, KNNs induce a faster decay of the loss than that by the feed-forward networks.
  arXiv  Detail & Related papers  (2021-05-20T04:54:57Z)
• Random Features for the Neural Tangent Kernel [57.132634274795066]
  We propose an efficient feature map construction of the Neural Tangent Kernel (NTK) of fully-connected ReLU network. We show that dimension of the resulting features is much smaller than other baseline feature map constructions to achieve comparable error bounds both in theory and practice.
  arXiv  Detail & Related papers  (2021-04-03T09:08:12Z)
• 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)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)
• Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks [12.692279981822011]
  We derive the covariance functions of multi-layer perceptrons with exponential linear units (ELU) and Gaussian error linear units (GELU) We analyse the fixed-point dynamics of iterated kernels corresponding to a broad range of activation functions. We find that unlike some previously studied neural network kernels, these new kernels exhibit non-trivial fixed-point dynamics.
  arXiv  Detail & Related papers  (2020-02-20T01:25:39Z)

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.