A generalized neural tangent kernel for surrogate gradient learning

• URL: http://arxiv.org/abs/2405.15539v1
• Date: Fri, 24 May 2024 13:27:23 GMT
• Title: A generalized neural tangent kernel for surrogate gradient learning
• Authors: Luke Eilers, Raoul-Martin Memmesheimer, Sven Goedeke,
• Abstract summary: We provide a generalization of the neural tangent kernel (NTK) that enables the analysis of surrogate gradient learning (SGL) We numerically compare SGL in networks with sign activation function and finite width to kernel regression with the surrogate gradient NTK.
• Score: 2.048226951354646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art neural network training methods depend on the gradient of the network function. Therefore, they cannot be applied to networks whose activation functions do not have useful derivatives, such as binary and discrete-time spiking neural networks. To overcome this problem, the activation function's derivative is commonly substituted with a surrogate derivative, giving rise to surrogate gradient learning (SGL). This method works well in practice but lacks theoretical foundation. The neural tangent kernel (NTK) has proven successful in the analysis of gradient descent. Here, we provide a generalization of the NTK, which we call the surrogate gradient NTK, that enables the analysis of SGL. First, we study a naive extension of the NTK to activation functions with jumps, demonstrating that gradient descent for such activation functions is also ill-posed in the infinite-width limit. To address this problem, we generalize the NTK to gradient descent with surrogate derivatives, i.e., SGL. We carefully define this generalization and expand the existing key theorems on the NTK with mathematical rigor. Further, we illustrate our findings with numerical experiments. Finally, we numerically compare SGL in networks with sign activation function and finite width to kernel regression with the surrogate gradient NTK; the results confirm that the surrogate gradient NTK provides a good characterization of SGL.

Related papers

• Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network? [9.599018775881275]
  A rising trend in theoretical deep learning is to understand why deep learning works through Neural Tangent Kernel (NTK) [jgh18]. GNTK is a kernel method that is equivalent to using gradient descent to train a multi-layer infinitely-wide neural network. We show that GNTK can achieve similar accuracy as GNNs on various bioinformatics datasets.
  arXiv  Detail & Related papers  (2023-09-14T06:24:33Z)
• Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum [18.10812063219831]
  We introduce Modified Spectrum Kernels (MSKs) to approximate kernels with desired eigenvalues. We propose a preconditioned gradient descent method, which alters the trajectory of gradient descent. Our method is both computationally efficient and simple to implement.
  arXiv  Detail & Related papers  (2023-07-26T22:39:47Z)
• 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)
• Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials [52.11466135206223]
  We show that a wide two-layer neural network can jointly use the Tangent Kernel (NTK) and the QuadNTK to fit target functions. This yields an end to end convergence and guarantee with provable sample improvement over both the NTK and QuadNTK on their own.
  arXiv  Detail & Related papers  (2022-06-08T06:06:51Z)
• Scaling Neural Tangent Kernels via Sketching and Random Features [53.57615759435126]
  Recent works report that NTK regression can outperform finitely-wide neural networks trained on small-scale datasets. We design a near input-sparsity time approximation algorithm for NTK, by sketching the expansions of arc-cosine kernels. We show that a linear regressor trained on our CNTK features matches the accuracy of exact CNTK on CIFAR-10 dataset while achieving 150x speedup.
  arXiv  Detail & Related papers  (2021-06-15T04:44:52Z)
• A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions [3.4792548480344254]
  We show that the risk function of the gradient descent method does indeed converge to zero. A key contribution of this work is to explicitly specify a Lyapunov function for the gradient flow system of the ANN parameters.
  arXiv  Detail & Related papers  (2021-02-19T13:33:03Z)
• Learning Quantized Neural Nets by Coarse Gradient Method for Non-linear Classification [3.158346511479111]
  We propose a class of STEs with certain monotonicity, and consider their applications to the training of a two-linear-layer network with quantized activation functions. We establish performance guarantees for the proposed STEs by showing that the corresponding coarse gradient methods converge to the global minimum.
  arXiv  Detail & Related papers  (2020-11-23T07:50:09Z)
• When and why PINNs fail to train: A neural tangent kernel perspective [2.1485350418225244]
  We derive the Neural Tangent Kernel (NTK) of PINNs and prove that, under appropriate conditions, it converges to a deterministic kernel that stays constant during training in the infinite-width limit. We find a remarkable discrepancy in the convergence rate of the different loss components contributing to the total training error. We propose a novel gradient descent algorithm that utilizes the eigenvalues of the NTK to adaptively calibrate the convergence rate of the total training error.
  arXiv  Detail & Related papers  (2020-07-28T23:44:56Z)
• Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime [50.510421854168065]
  We show that the averaged gradient descent can achieve the minimax optimal convergence rate. We show that the target function specified by the NTK of a ReLU network can be learned at the optimal convergence rate.
  arXiv  Detail & Related papers  (2020-06-22T14:31:37Z)
• On Learning Rates and Schr\"odinger Operators [105.32118775014015]
  We present a general theoretical analysis of the effect of the learning rate. We find that the learning rate tends to zero for a broad non- neural class functions.
  arXiv  Detail & Related papers  (2020-04-15T09:52:37Z)
• A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks [87.23360438947114]
  We show that noisy gradient descent with weight decay can still exhibit a " Kernel-like" behavior. This implies that the training loss converges linearly up to a certain accuracy. We also establish a novel generalization error bound for two-layer neural networks trained by noisy gradient descent with weight decay.
  arXiv  Detail & Related papers  (2020-02-10T18:56:15Z)

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.