Can Forward Gradient Match Backpropagation?

• URL: http://arxiv.org/abs/2306.06968v1
• Date: Mon, 12 Jun 2023 08:53:41 GMT
• Title: Can Forward Gradient Match Backpropagation?
• Authors: Louis Fournier (MLIA), St\'ephane Rivaud (MLIA), Eugene Belilovsky (MILA), Michael Eickenberg, Edouard Oyallon (MLIA)
• Abstract summary: Forward Gradients have been shown to be utilizable for neural network training. We propose to strongly bias our gradient guesses in directions that are much more promising, such as feedback obtained from small, local auxiliary networks. We find that using gradients obtained from a local loss as a candidate direction drastically improves on random noise in Forward Gradient methods.
• Score: 2.875726839945885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements. The cost is the requirement to guess the step direction, which is hard in high dimensions. While current solutions rely on weighted averages over isotropic guess vector distributions, we propose to strongly bias our gradient guesses in directions that are much more promising, such as feedback obtained from small, local auxiliary networks. For a standard computer vision neural network, we conduct a rigorous study systematically covering a variety of combinations of gradient targets and gradient guesses, including those previously presented in the literature. We find that using gradients obtained from a local loss as a candidate direction drastically improves on random noise in Forward Gradient methods.

Related papers

• Correlations Are Ruining Your Gradient Descent [1.2432046687586285]
  Natural gradient descent illuminates how gradient vectors, pointing at directions of steepest descent, can be improved by considering the local curvature of loss landscapes. We show that correlations in the data at any linear transformation, including node responses at every layer of a neural network, cause a non-orthonormal relationship between the model's parameters. We describe a range of methods which have been proposed for decorrelation and whitening of node output, and expand on these to provide a novel method specifically useful for distributed computing and computational neuroscience.
  arXiv  Detail & Related papers  (2024-07-15T14:59:43Z)
• A Learning Paradigm for Interpretable Gradients [9.074325843851726]
  We present a novel training approach to improve the quality of gradients for interpretability. We find that the resulting gradient is qualitatively less noisy and improves quantitatively the interpretability properties of different networks.
  arXiv  Detail & Related papers  (2024-04-23T13:32:29Z)
• How to guess a gradient [68.98681202222664]
  We show that gradients are more structured than previously thought. Exploiting this structure can significantly improve gradient-free optimization schemes. We highlight new challenges in overcoming the large gap between optimizing with exact gradients and guessing the gradients.
  arXiv  Detail & Related papers  (2023-12-07T21:40:44Z)
• NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function [55.86697795177619]
  Normal estimation for 3D point clouds is a fundamental task in 3D geometry processing. We introduce a new paradigm for learning neural gradient functions, which encourages the neural network to fit the input point clouds. Our excellent results on widely used benchmarks demonstrate that our method can learn more accurate normals for both unoriented and oriented normal estimation tasks.
  arXiv  Detail & Related papers  (2023-11-01T09:25:29Z)
• Stochastic Gradient Descent for Gaussian Processes Done Right [86.83678041846971]
  We show that when emphdone right -- by which we mean using specific insights from optimisation and kernel communities -- gradient descent is highly effective. We introduce a emphstochastic dual descent algorithm, explain its design in an intuitive manner and illustrate the design choices. Our method places Gaussian process regression on par with state-of-the-art graph neural networks for molecular binding affinity prediction.
  arXiv  Detail & Related papers  (2023-10-31T16:15:13Z)
• Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data [63.34506218832164]
  In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with ReLU activations. For gradient flow, we leverage recent work on the implicit bias for homogeneous neural networks to show that leakyally, gradient flow produces a neural network with rank at most two. For gradient descent, provided the random variance is small enough, we show that a single step of gradient descent suffices to drastically reduce the rank of the network, and that the rank remains small throughout training.
  arXiv  Detail & Related papers  (2022-10-13T15:09:54Z)
• Scaling Forward Gradient With Local Losses [117.22685584919756]
  Forward learning is a biologically plausible alternative to backprop for learning deep neural networks. We show that it is possible to substantially reduce the variance of the forward gradient by applying perturbations to activations rather than weights. Our approach matches backprop on MNIST and CIFAR-10 and significantly outperforms previously proposed backprop-free algorithms on ImageNet.
  arXiv  Detail & Related papers  (2022-10-07T03:52:27Z)
• Channel-Directed Gradients for Optimization of Convolutional Neural Networks [50.34913837546743]
  We introduce optimization methods for convolutional neural networks that can be used to improve existing gradient-based optimization in terms of generalization error. We show that defining the gradients along the output channel direction leads to a performance boost, while other directions can be detrimental.
  arXiv  Detail & Related papers  (2020-08-25T00:44:09Z)

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.