Scaling of hardware-compatible perturbative training algorithms

• URL: http://arxiv.org/abs/2501.15403v1
• Date: Sun, 26 Jan 2025 05:11:42 GMT
• Title: Scaling of hardware-compatible perturbative training algorithms
• Authors: Bakhrom G. Oripov, Andrew Dienstfrey, Adam N. McCaughan, Sonia M. Buckley,
• Abstract summary: multiplexed gradient descent (MGD) is a scalable and efficient zeroth-order training method for estimating the gradient of a loss function in hardware. We investigate the time to train networks using MGD as a function of network size and task complexity. Our results indicate that MGD can efficiently train large networks on hardware, achieving accuracy comparable to backpropagation.
• Score: 0.0
• License:
• Abstract: In this work, we explore the capabilities of multiplexed gradient descent (MGD), a scalable and efficient perturbative zeroth-order training method for estimating the gradient of a loss function in hardware and training it via stochastic gradient descent. We extend the framework to include both weight and node perturbation, and discuss the advantages and disadvantages of each approach. We investigate the time to train networks using MGD as a function of network size and task complexity. Previous research has suggested that perturbative training methods do not scale well to large problems, since in these methods the time to estimate the gradient scales linearly with the number of network parameters. However, in this work we show that the time to reach a target accuracy--that is, actually solve the problem of interest--does not follow this undesirable linear scaling, and in fact often decreases with network size. Furthermore, we demonstrate that MGD can be used to calculate a drop-in replacement for the gradient in stochastic gradient descent, and therefore optimization accelerators such as momentum can be used alongside MGD, ensuring compatibility with existing machine learning practices. Our results indicate that MGD can efficiently train large networks on hardware, achieving accuracy comparable to backpropagation, thus presenting a practical solution for future neuromorphic computing systems.

Related papers

• Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling [44.31966204357333]
  We develop memory-efficient algorithms for large-scale machine learning problems. We use two key techniques to make our approach memory-efficient and avoid full computations.
  arXiv  Detail & Related papers  (2025-02-20T15:37:45Z)
• Fast and Slow Gradient Approximation for Binary Neural Network Optimization [11.064044986709733]
  hypernetwork based methods utilize neural networks to learn the gradients of non-differentiable quantization functions. We propose a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. We also introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients.
  arXiv  Detail & Related papers  (2024-12-16T13:48:40Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• 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)
• Adaptive Self-supervision Algorithms for Physics-informed Neural Networks [59.822151945132525]
  Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function. We study the impact of the location of the collocation points on the trainability of these models. We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
  arXiv  Detail & Related papers  (2022-07-08T18:17:06Z)
• Low-memory stochastic backpropagation with multi-channel randomized trace estimation [6.985273194899884]
  We propose to approximate the gradient of convolutional layers in neural networks with a multi-channel randomized trace estimation technique. Compared to other methods, this approach is simple, amenable to analyses, and leads to a greatly reduced memory footprint. We discuss the performance of networks trained with backpropagation and how the error can be controlled while maximizing memory usage and minimizing computational overhead.
  arXiv  Detail & Related papers  (2021-06-13T13:54:02Z)
• Predicting Training Time Without Training [120.92623395389255]
  We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. We leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. We are able to predict the time it takes to fine-tune a model to a given loss without having to perform any training.
  arXiv  Detail & Related papers  (2020-08-28T04:29:54Z)
• 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.