Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers

• URL: http://arxiv.org/abs/2411.00999v1
• Date: Fri, 01 Nov 2024 19:50:00 GMT
• Title: Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
• Authors: Gavia Gray, Aman Tiwari, Shane Bergsma, Joel Hestness,
• Abstract summary: Per-example gradient norms are a vital ingredient for estimating gradient noise scale (GNS) with minimal variance. We propose a method with minimal FLOPs in 3D or greater tensor regimes by simultaneously computing the norms while computing the parameter gradients. We find that the total GNS of contemporary transformer models is predicted well by the GNS of only the normalization layers.
• Score: 2.1415873597974286
• License:
• Abstract: Per-example gradient norms are a vital ingredient for estimating gradient noise scale (GNS) with minimal variance. Observing the tensor contractions required to compute them, we propose a method with minimal FLOPs in 3D or greater tensor regimes by simultaneously computing the norms while computing the parameter gradients. Using this method we are able to observe the GNS of different layers at higher accuracy than previously possible. We find that the total GNS of contemporary transformer models is predicted well by the GNS of only the normalization layers. As a result, focusing only on the normalization layer, we develop a custom kernel to compute the per-example gradient norms while performing the LayerNorm backward pass with zero throughput overhead. Tracking GNS on only those layers, we are able to guide a practical batch size schedule that reduces training time by 18% on a Chinchilla-optimal language model.

Related papers

• Gradient Normalization with(out) Clipping Ensures Convergence of Nonconvex SGD under Heavy-Tailed Noise with Improved Results [60.92029979853314]
  This paper investigates Gradient Normalization without (NSGDC) its gradient reduction variant (NSGDC-VR) We present significant improvements in the theoretical results for both algorithms.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)
• 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)
• Neural Gradient Learning and Optimization for Oriented Point Normal Estimation [53.611206368815125]
  We propose a deep learning approach to learn gradient vectors with consistent orientation from 3D point clouds for normal estimation. We learn an angular distance field based on local plane geometry to refine the coarse gradient vectors. Our method efficiently conducts global gradient approximation while achieving better accuracy and ability generalization of local feature description.
  arXiv  Detail & Related papers  (2023-09-17T08:35:11Z)
• Error-aware Quantization through Noise Tempering [43.049102196902844]
  Quantization-aware training (QAT) optimize model parameters with respect to the end task while simulating quantization error. In this work, we incorporate exponentially decaying quantization-error-aware noise together with a learnable scale of task loss gradient to approximate the effect of a quantization operator. Our method obtains state-of-the-art top-1 classification accuracy for uniform (non mixed-precision) quantization, out-performing previous methods by 0.5-1.2% absolute.
  arXiv  Detail & Related papers  (2022-12-11T20:37:50Z)
• 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)
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks [74.935141515523]
  gradient centralization (GC) operates directly on gradients by centralizing the gradient vectors to have zero mean. GC can be viewed as a projected gradient descent method with a constrained loss function. GC is very simple to implement and can be easily embedded into existing gradient based DNNs with only one line of code.
  arXiv  Detail & Related papers  (2020-04-03T10:25:00Z)

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.