Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes

• URL: http://arxiv.org/abs/2508.04193v1
• Date: Wed, 06 Aug 2025 08:23:38 GMT
• Title: Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
• Authors: Chengcheng Yan, Jiawei Xu, Zheng Peng, Qingsong Wang,
• Abstract summary: The training of deep neural networks is inherently a non- optimization problem.<n>Standard approaches such as gradient descent (SGD) require simultaneous updates to parameters.<n>We propose a novel method Alternating Train Miniization with tailored step sizes (SAMT)<n>SAMT achieves better performance with fewer parameter updates compared to state-of-the-art methods.
• Score: 3.246129789918632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and high computational cost. To address these issues, we propose a novel method, Stochastic Alternating Minimization with Trainable Step Sizes (SAMT), which updates network parameters in an alternating manner by treating the weights of each layer as a block. By decomposing the overall optimization into sub-problems corresponding to different blocks, this block-wise alternating strategy reduces per-step computational overhead and enhances training stability in nonconvex settings. To fully leverage these benefits, inspired by meta-learning, we proposed a novel adaptive step size strategy to incorporate into the sub-problem solving steps of alternating updates. It supports different types of trainable step sizes, including but not limited to scalar, element-wise, row-wise, and column-wise, enabling adaptive step size selection tailored to each block via meta-learning. We further provide a theoretical convergence guarantee for the proposed algorithm, establishing its optimization soundness. Extensive experiments for multiple benchmarks demonstrate that SAMT achieves better generalization performance with fewer parameter updates compared to state-of-the-art methods, highlighting its effectiveness and potential in neural network optimization.

Related papers

• Blockwise Optimization for Projective Variational Quantum Dynamics (BLOP-VQD): Algorithm and Implementation for Lattice Systems [0.0]
  We present an efficient approach to simulate real-time quantum dynamics using Projected Variational Quantum Dynamics.<n>Our method selectively optimize one block at a time while keeping the others fixed, allowing for significant reductions in computational overhead.<n>We demonstrate the performance of the proposed methods in a series of spin-lattice models with varying sizes and complexity.
  arXiv  Detail & Related papers  (2025-03-24T01:48:37Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We propose a new family of algorithms that uses the linear minimization oracle (LMO) to adapt to the geometry of the problem.<n>We demonstrate significant speedups on nanoGPT training using our algorithm, Scion, without any reliance on Adam.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• Constrained Hybrid Metaheuristic Algorithm for Probabilistic Neural Networks Learning [0.3686808512438362]
  This study investigates the potential of hybrid metaheuristic algorithms to enhance the training of Probabilistic Neural Networks (PNNs)<n>Traditional learning methods, such as gradient-based approaches, often struggle to optimise high-dimensional and uncertain environments.<n>We propose the constrained Hybrid Metaheuristic (cHM) algorithm, which combines multiple population-based optimisation techniques into a unified framework.
  arXiv  Detail & Related papers  (2025-01-26T19:49:16Z)
• Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning [8.173034693197351]
  We propose a new per-layer adaptive step-size procedure for first-order optimization methods in deep learning. The proposed approach exploits the layer-wise curvature information contained in the diagonal blocks of the Hessian in deep neural networks (DNNs) to compute adaptive step-sizes (i.e., LRs) for each layer. Numerical experiments show that SGD with momentum and AdamW combined with the proposed per-layer step-sizes are able to choose effective LR schedules.
  arXiv  Detail & Related papers  (2023-05-23T04:12:55Z)
• Hyper-Learning for Gradient-Based Batch Size Adaptation [2.944323057176686]
  Scheduling the batch size to increase is an effective strategy to control noise when training deep neural networks. We introduce Arbiter as a new hyper-optimization algorithm to perform batch size adaptations for learnable schedulings. We demonstrate Arbiter's effectiveness in several illustrative experiments.
  arXiv  Detail & Related papers  (2022-05-17T11:01:14Z)
• An Adaptive Incremental Gradient Method With Support for Non-Euclidean Norms [19.41328109094503]
  We propose and analyze several novel adaptive variants of the popular SAGA algorithm. We establish its convergence guarantees under general settings. We improve the analysis of SAGA to support non-Euclidean norms.
  arXiv  Detail & Related papers  (2022-04-28T09:43:07Z)
• Joint inference and input optimization in equilibrium networks [68.63726855991052]
  deep equilibrium model is a class of models that foregoes traditional network depth and instead computes the output of a network by finding the fixed point of a single nonlinear layer. We show that there is a natural synergy between these two settings. We demonstrate this strategy on various tasks such as training generative models while optimizing over latent codes, training models for inverse problems like denoising and inpainting, adversarial training and gradient based meta-learning.
  arXiv  Detail & Related papers  (2021-11-25T19:59:33Z)
• Adaptive pruning-based optimization of parameterized quantum circuits [62.997667081978825]
  Variisy hybrid quantum-classical algorithms are powerful tools to maximize the use of Noisy Intermediate Scale Quantum devices. We propose a strategy for such ansatze used in variational quantum algorithms, which we call "Efficient Circuit Training" (PECT) Instead of optimizing all of the ansatz parameters at once, PECT launches a sequence of variational algorithms.
  arXiv  Detail & Related papers  (2020-10-01T18:14:11Z)
• Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems [120.21685755278509]
  In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster in time up to an error. Rather than fixing the minibatch the step-size at the outset, we propose to allow parameters to evolve adaptively.
  arXiv  Detail & Related papers  (2020-07-02T16:02:02Z)
• AdaS: Adaptive Scheduling of Stochastic Gradients [50.80697760166045]
  We introduce the notions of textit"knowledge gain" and textit"mapping condition" and propose a new algorithm called Adaptive Scheduling (AdaS) Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training.
  arXiv  Detail & Related papers  (2020-06-11T16:36:31Z)
• Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization [71.03797261151605]
  Adaptivity is an important yet under-studied property in modern optimization theory. Our algorithm is proved to achieve the best-available convergence for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives.
  arXiv  Detail & Related papers  (2020-02-13T05:42:27Z)

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.