Towards Exact Gradient-based Training on Analog In-memory Computing

• URL: http://arxiv.org/abs/2406.12774v1
• Date: Tue, 18 Jun 2024 16:43:59 GMT
• Title: Towards Exact Gradient-based Training on Analog In-memory Computing
• Authors: Zhaoxian Wu, Tayfun Gokmen, Malte J. Rasch, Tianyi Chen,
• Abstract summary: Inference on analog accelerators has been studied recently, but the training perspective is underexplored. Recent studies have shown that the "workhorse" of digital AI training - gradient descent (SGD) algorithm converges inexactly when applied to model training on non-ideal devices. This paper puts forth a theoretical foundation for gradient-based training on analog devices.
• Score: 28.38387901763604
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the high economic and environmental costs of using large vision or language models, analog in-memory accelerators present a promising solution for energy-efficient AI. While inference on analog accelerators has been studied recently, the training perspective is underexplored. Recent studies have shown that the "workhorse" of digital AI training - stochastic gradient descent (SGD) algorithm converges inexactly when applied to model training on non-ideal devices. This paper puts forth a theoretical foundation for gradient-based training on analog devices. We begin by characterizing the non-convergent issue of SGD, which is caused by the asymmetric updates on the analog devices. We then provide a lower bound of the asymptotic error to show that there is a fundamental performance limit of SGD-based analog training rather than an artifact of our analysis. To address this issue, we study a heuristic analog algorithm called Tiki-Taka that has recently exhibited superior empirical performance compared to SGD and rigorously show its ability to exactly converge to a critical point and hence eliminates the asymptotic error. The simulations verify the correctness of the analyses.

Related papers

• Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration [67.12978375116599]
  We show that the steps of gradient descent (GD) reduce to those of generalized perceptron algorithms.<n>This helps explain the optimization dynamics and the implicit acceleration phenomenon observed in neural networks.
  arXiv  Detail & Related papers  (2025-12-12T14:16:35Z)
• In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning [59.091567092071564]
  In-memory training typically requires at least 8-bit conductance states to match digital baselines.<n>Many promising memristive devices such as ReRAM offer only about 4-bit resolution due to fabrication constraints.<n>This paper proposes a emphresidual learning framework that sequentially learns on multiple crossbar tiles to compensate the residual errors.
  arXiv  Detail & Related papers  (2025-10-02T19:44:25Z)
• Assessing the Performance of Analog Training for Transfer Learning [0.26388783516590225]
  Analog in-memory computing promises fast, parallel, and energy-efficient deep learning training and transfer learning.<n>A new algorithm chopped TTv2 (c-TTv2) has been introduced, which leverages the chopped technique to address many of the challenges mentioned above.<n>In this paper, we assess the performance of the c-TTv2 algorithm for analog TL using a Swin-ViT model on a subset of the CIFAR100 dataset.
  arXiv  Detail & Related papers  (2025-05-16T10:02:32Z)
• Learning in Log-Domain: Subthreshold Analog AI Accelerator Based on Stochastic Gradient Descent [5.429033337081392]
  We propose a novel analog accelerator architecture for AI/ML training workloads using gradient descent with L2 regularization (SGDr) The proposed design achieves significant reductions in transistor area and power consumption compared to digital implementations. This work paves the way for energy-efficient analog AI hardware with on-chip training capabilities.
  arXiv  Detail & Related papers  (2025-01-22T19:26:36Z)
• Thermodynamic Natural Gradient Descent [0.0]
  We show that natural gradient descent can have a similar computational complexity per iteration to a first-order method. We present a new hybrid digital-analog algorithm for training neural networks.
  arXiv  Detail & Related papers  (2024-05-22T16:47:03Z)
• 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)
• SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates [19.420605210427635]
  SketchySGD improves upon existing gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian. We show theoretically that SketchySGD with a fixed stepsize converges linearly to a small ball around the optimum. In the ill-conditioned setting we show SketchySGD converges at a faster rate than SGD for least-squares problems.
  arXiv  Detail & Related papers  (2022-11-16T01:05:41Z)
• Deep Equilibrium Optical Flow Estimation [80.80992684796566]
  Recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms. These RNNs impose large computation and memory overheads, and are not directly trained to model such stable estimation. We propose deep equilibrium (DEQ) flow estimators, an approach that directly solves for the flow as the infinite-level fixed point of an implicit layer.
  arXiv  Detail & Related papers  (2022-04-18T17:53:44Z)
• Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning [65.54757265434465]
  Pairwise learning refers to learning tasks where the loss function depends on a pair instances. Online descent (OGD) is a popular approach to handle streaming data in pairwise learning. In this paper, we propose simple and online descent to methods for pairwise learning.
  arXiv  Detail & Related papers  (2021-11-23T18:10:48Z)
• Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits [21.353189917487512]
  gradient descent (SGD) and its variants have established themselves as the go-to algorithms for machine learning problems. We take a step forward by proving minibatch SGD converges to a critical point of the full log-likelihood loss function. Our theoretical guarantees hold provided that the kernel functions exhibit exponential or eigendecay.
  arXiv  Detail & Related papers  (2021-11-19T22:28:47Z)
• Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function [3.5044892799305956]
  We provide a non-asymptotic analysis for the tamed un-adjusted Langevin algorithm (TUSLA) introduced in Lovas et al. In particular, we establish non-asymptotic error bounds for the TUSLA algorithm in Wassersteinstein-1-2. We show that the TUSLA algorithm converges rapidly to the optimal solution.
  arXiv  Detail & Related papers  (2021-07-19T07:13:02Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)
• 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.