Rescaling-Aware Training for Efficient Deployment of Deep Learning Models on Full-Integer Hardware

• URL: http://arxiv.org/abs/2510.11484v1
• Date: Mon, 13 Oct 2025 14:55:34 GMT
• Title: Rescaling-Aware Training for Efficient Deployment of Deep Learning Models on Full-Integer Hardware
• Authors: Lion Mueller, Alberto Garcia-Ortiz, Ardalan Najafi, Adam Fuks, Lennart Bamberg,
• Abstract summary: Quantization-aware training (QAT) helps accuracy degradation associated with post-training quantization but overlooks the impact of integer rescaling during inference.<n>We introduce Rescale-Aware Training, a fine tuning method for ultra-low bit-width rescaling multiplicands.<n>Experiments show that even with 8x reduced rescaler widths, the full accuracy is preserved through minimal incremental retraining.
• Score: 0.26097841018267615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Integer AI inference significantly reduces computational complexity in embedded systems. Quantization-aware training (QAT) helps mitigate accuracy degradation associated with post-training quantization but still overlooks the impact of integer rescaling during inference, which is a hardware costly operation in integer-only AI inference. This work shows that rescaling cost can be dramatically reduced post-training, by applying a stronger quantization to the rescale multiplicands at no model-quality loss. Furthermore, we introduce Rescale-Aware Training, a fine tuning method for ultra-low bit-width rescaling multiplicands. Experiments show that even with 8x reduced rescaler widths, the full accuracy is preserved through minimal incremental retraining. This enables more energy-efficient and cost-efficient AI inference for resource-constrained embedded systems.

Related papers

• Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers [10.320585073024455]
  We present a framework that enables scalable and energy-efficient PINN training on edge devices.<n>This work enables real-time PDE solving on edge devices and paves the way for energy-efficient scientific computing at scale.
  arXiv  Detail & Related papers  (2025-12-10T00:00:34Z)
• 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)
• QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge [55.75103034526652]
  We propose QuartDepth which adopts post-training quantization to quantize MDE models with hardware accelerations for ASICs.<n>Our approach involves quantizing both weights and activations to 4-bit precision, reducing the model size and computation cost.<n>We design a flexible and programmable hardware accelerator by supporting kernel fusion and customized instruction programmability.
  arXiv  Detail & Related papers  (2025-03-20T21:03:10Z)
• TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training [91.8932638236073]
  We introduce textbfTensorGRaD, a novel method that directly addresses the memory challenges associated with large-structured weights.<n>We show that sparseGRaD reduces total memory usage by over $50%$ while maintaining and sometimes even improving accuracy.
  arXiv  Detail & Related papers  (2025-01-04T20:51:51Z)
• Taming 3DGS: High-Quality Radiance Fields with Limited Resources [50.92437599516609]
  3D Gaussian Splatting (3DGS) has transformed novel-view synthesis with its fast, interpretable, and high-fidelity rendering. We tackle the challenges of training and rendering 3DGS models on a budget. We derive faster, numerically equivalent solutions for gradient computation and attribute updates.
  arXiv  Detail & Related papers  (2024-06-21T20:44:23Z)
• Hadamard Domain Training with Integers for Class Incremental Quantized Learning [1.4416751609100908]
  Continual learning can be cost-prohibitive for resource-constraint edge platforms. We propose a technique that transforms to enable low-precision training with only integer matrix multiplications. We achieve less than 0.5% and 3% accuracy degradation while we quantize all matrix multiplications inputs down to 4-bits with 8-bit accumulators.
  arXiv  Detail & Related papers  (2023-10-05T16:52:59Z)
• On-Device Training Under 256KB Memory [62.95579393237751]
  We propose an algorithm-system co-design framework to make on-device training possible with only 256KB of memory. Our framework is the first solution to enable tiny on-device training of convolutional neural networks under 256KB and 1MB Flash.
  arXiv  Detail & Related papers  (2022-06-30T17:59:08Z)
• Online Convolutional Re-parameterization [51.97831675242173]
  We present online convolutional re- parameterization (OREPA), a two-stage pipeline, aiming to reduce the huge training overhead by squeezing the complex training-time block into a single convolution. Compared with the state-of-the-art re-param models, OREPA is able to save the training-time memory cost by about 70% and accelerate the training speed by around 2x. We also conduct experiments on object detection and semantic segmentation and show consistent improvements on the downstream tasks.
  arXiv  Detail & Related papers  (2022-04-02T09:50:19Z)
• Enabling Incremental Training with Forward Pass for Edge Devices [0.0]
  We introduce a method using evolutionary strategy (ES) that can partially retrain the network enabling it to adapt to changes and recover after an error has occurred. This technique enables training on an inference-only hardware without the need to use backpropagation and with minimal resource overhead.
  arXiv  Detail & Related papers  (2021-03-25T17:43:04Z)
• DAQ: Distribution-Aware Quantization for Deep Image Super-Resolution Networks [49.191062785007006]
  Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. Existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths, or require a heavy fine-tuning process to recover the performance. We propose a novel distribution-aware quantization scheme (DAQ) which facilitates accurate training-free quantization in ultra-low precision.
  arXiv  Detail & Related papers  (2020-12-21T10:19:42Z)
• Recovery of Linear Components: Reduced Complexity Autoencoder Designs [0.951828574518325]
  We present an approach called Recovery of Linear Components (RLC), which serves as a middle ground between linear and non-linear dimensionality reduction techniques. With the aid of synthetic and real world case studies, we show that the RLC, when compared with an autoencoder of similar complexity, shows higher accuracy, similar to robustness to overfitting, and faster training times.
  arXiv  Detail & Related papers  (2020-12-14T14:08:20Z)
• Pruning Convolutional Filters using Batch Bridgeout [14.677724755838556]
  State-of-the-art computer vision models are rapidly increasing in capacity, where the number of parameters far exceeds the number required to fit the training set. This results in better optimization and generalization performance. In order to reduce inference costs, convolutional filters in trained neural networks could be pruned to reduce the run-time memory and computational requirements during inference. We propose the use of Batch Bridgeout, a sparsity inducing regularization scheme, to train neural networks so that they could be pruned efficiently with minimal degradation in performance.
  arXiv  Detail & Related papers  (2020-09-23T01:51:47Z)
• Improving compute efficacy frontiers with SliceOut [31.864949424541344]
  We introduce SliceOut -- a dropout-inspired scheme to train deep learning models faster without impacting final test accuracy. At test time, turning off SliceOut performs an implicit ensembling across a linear number of architectures that preserves test accuracy. This leads to faster processing of large computational workloads overall, and significantly reduce the resulting energy consumption and CO2emissions.
  arXiv  Detail & Related papers  (2020-07-21T15:59:09Z)

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.