Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering

• URL: http://arxiv.org/abs/2412.18052v2
• Date: Sun, 29 Dec 2024 11:44:55 GMT
• Title: Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering
• Authors: Francois Chaubard, Duncan Eddy, Mykel J. Kochenderfer,
• Abstract summary: Traditional distributed data-parallel gradient descent involves averaging gradients of microbatches to calculate a macrobatch that is then used to update model parameters. We introduce a simple, computationally effective way to reduce gradient variance by computing the cosine distance between micro-gradients during training. We show this technique consistently outperforms validation accuracy in some cases by up to 18.2% compared to traditional training approaches.
• Score: 36.896695278624776
• License:
• Abstract: We introduce Gradient Agreement Filtering (GAF) to improve on gradient averaging in distributed deep learning optimization. Traditional distributed data-parallel stochastic gradient descent involves averaging gradients of microbatches to calculate a macrobatch gradient that is then used to update model parameters. We find that gradients across microbatches are often orthogonal or negatively correlated, especially in late stages of training, which leads to memorization of the training set, reducing generalization. In this paper, we introduce a simple, computationally effective way to reduce gradient variance by computing the cosine distance between micro-gradients during training and filtering out conflicting updates prior to averaging. We improve validation accuracy with significantly smaller microbatch sizes. We also show this reduces memorizing noisy labels. We demonstrate the effectiveness of this technique on standard image classification benchmarks including CIFAR-100 and CIFAR-100N-Fine. We show this technique consistently outperforms validation accuracy, in some cases by up to 18.2\% compared to traditional training approaches while reducing the computation required nearly an order of magnitude because we can now rely on smaller microbatch sizes without destabilizing training.

Related papers

• Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization [1.6749379740049926]
  We introduce F-CMA, a Fast-Controlled Mini-batch Algorithm with a random reshuffling method featuring a sufficient decrease condition and a line-search procedure to ensure loss reduction per epoch. Tests show significant improvements, including a decrease in the overall training time by 68%, an increase in per-epoch efficiency by up to 20%, and in model accuracy by up to 5%.
  arXiv  Detail & Related papers  (2024-11-24T11:46:47Z)
• Aiming towards the minimizers: fast convergence of SGD for overparametrized problems [25.077446336619378]
  We propose a regularity regime which endows the gradient method with the same worst-case complexity as the gradient method. All existing guarantees require the gradient method to take small steps, thereby resulting in a much slower linear rate of convergence. We demonstrate that our condition holds when training sufficiently wide feedforward neural networks with a linear output layer.
  arXiv  Detail & Related papers  (2023-06-05T05:21:01Z)
• 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)
• Low-Precision Arithmetic for Fast Gaussian Processes [39.720581185327816]
  Low-precision arithmetic has had a transformative effect on the training of neural networks. We propose a multi-faceted approach involving conjugate gradients with re-orthogonalization, mixed precision, and preconditioning. Our approach significantly improves the numerical stability and practical performance of conjugate gradients in low-precision over a wide range of settings.
  arXiv  Detail & Related papers  (2022-07-14T12:20:46Z)
• Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization [61.26619639722804]
  We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
  arXiv  Detail & Related papers  (2022-02-26T19:10:48Z)
• When are Iterative Gaussian Processes Reliably Accurate? [38.523693700243975]
  Lanczos decompositions have achieved scalable Gaussian process inference with highly accurate point predictions. We investigate CG tolerance, preconditioner rank, and Lanczos decomposition rank. We show that LGS-BFB is a compelling for Iterative GPs, achieving convergence with fewer updates.
  arXiv  Detail & Related papers  (2021-12-31T00:02:18Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• A Study of Gradient Variance in Deep Learning [56.437755740715396]
  We introduce a method, Gradient Clustering, to minimize the variance of average mini-batch gradient with stratified sampling. We measure the gradient variance on common deep learning benchmarks and observe that, contrary to common assumptions, gradient variance increases during training.
  arXiv  Detail & Related papers  (2020-07-09T03:23:10Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.