Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring

• URL: http://arxiv.org/abs/2510.00442v1
• Date: Wed, 01 Oct 2025 02:49:40 GMT
• Title: Randomized Matrix Sketching for Neural Network Training and Gradient Monitoring
• Authors: Harbir Antil, Deepanshu Verma,
• Abstract summary: We present the first adaptation of control-theoretic matrix sketching to neural network layer activations.<n>We show how sketched activation storage provides a viable path toward memory-efficient neural network training and analysis.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural network training relies on gradient computation through backpropagation, yet memory requirements for storing layer activations present significant scalability challenges. We present the first adaptation of control-theoretic matrix sketching to neural network layer activations, enabling memory-efficient gradient reconstruction in backpropagation. This work builds on recent matrix sketching frameworks for dynamic optimization problems, where similar state trajectory storage challenges motivate sketching techniques. Our approach sketches layer activations using three complementary sketch matrices maintained through exponential moving averages (EMA) with adaptive rank adjustment, automatically balancing memory efficiency against approximation quality. Empirical evaluation on MNIST, CIFAR-10, and physics-informed neural networks demonstrates a controllable accuracy-memory tradeoff. We demonstrate a gradient monitoring application on MNIST showing how sketched activations enable real-time gradient norm tracking with minimal memory overhead. These results establish that sketched activation storage provides a viable path toward memory-efficient neural network training and analysis.

Related papers

• Information-Theoretic Greedy Layer-wise Training for Traffic Sign Recognition [0.5024983453990065]
  layer-wise training eliminates the need for cross-entropy loss and backpropagation.<n>Most existing layer-wise training approaches have been evaluated only on relatively small datasets.<n>We propose a novel layer-wise training approach based on the recently developed deterministic information bottleneck (DIB) and the matrix-based R'enyi's $alpha$-order entropy functional.
  arXiv  Detail & Related papers  (2025-10-31T17:24:58Z)
• Memory Constrained Dynamic Subnetwork Update for Transfer Learning [20.05842386680307]
  MeDyate is a theoretically-grounded framework for memory-constrained dynamic subnetwork adaptation.<n>MeDyate achieves state-of-the-art performance under extreme memory constraints.
  arXiv  Detail & Related papers  (2025-10-23T20:16:43Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
  Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization. We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
  arXiv  Detail & Related papers  (2022-07-18T06:01:29Z)
• Memory-Efficient Backpropagation through Large Linear Layers [107.20037639738433]
  In modern neural networks like Transformers, linear layers require significant memory to store activations during backward pass. This study proposes a memory reduction approach to perform backpropagation through linear layers.
  arXiv  Detail & Related papers  (2022-01-31T13:02:41Z)
• 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)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• Gradient Projection Memory for Continual Learning [5.43185002439223]
  The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. We propose a novel approach where a neural network learns new tasks by taking gradient steps in the orthogonal direction to the gradient subspaces deemed important for the past tasks.
  arXiv  Detail & Related papers  (2021-03-17T16:31:29Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• On-Chip Error-triggered Learning of Multi-layer Memristive Spiking Neural Networks [1.7958576850695402]
  We propose a local, gradient-based, error-triggered learning algorithm with online ternary weight updates. The proposed algorithm enables online training of multi-layer SNNs with memristive neuromorphic hardware.
  arXiv  Detail & Related papers  (2020-11-21T19:44:19Z)
• Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks [77.34726150561087]
  We introduce Gradient Markov Descent (SMGD), a discrete optimization method applicable to training quantized neural networks. We provide theoretical guarantees of algorithm performance as well as encouraging numerical results.
  arXiv  Detail & Related papers  (2020-08-25T15:48:15Z)
• Neuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning [4.2903672492917755]
  We develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuromodulation. We demonstrate the efficacy of our approach on both single task and continual learning setting.
  arXiv  Detail & Related papers  (2020-07-16T07:41:23Z)

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.