Kilobyte Models: Neural Networks as a Seed and a Quantized Latent

• URL: http://arxiv.org/abs/2608.00860v1
• Date: Sat, 01 Aug 2026 20:42:52 GMT
• Title: Kilobyte Models: Neural Networks as a Seed and a Quantized Latent
• Abstract summary: We study an extreme form of model compression in which the deployable artifact is not the weights but a short recipe for regenerating them.<n>A model becomes a seed together with a quantized latent, whose size is set by the latent dimension and bit width rather than the parameter count.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The cost of storing and transmitting a trained neural network scales with its parameter count, a bottleneck for over-the-air updates, on-device libraries, and other bandwidth-bound deployments. We study an extreme form of model compression in which the deployable artifact is not the weights but a short recipe for regenerating them. Building on Mapping Networks, which express a network's weights as a nonlinear function of a compact trainable latent and a fixed random basis, we observe that only the latent need be stored, because the basis and initialization center are reproducible from an integer seed. A model becomes a seed together with a quantized latent, whose size is set by the latent dimension and bit width rather than the parameter count. We formalize this artifact and introduce a seeded block-wise basis that scales to networks whose projection cannot be held in memory. In our experiments, a mapped model is as accurate as the same network quantized aggressively to a few bits per weight, while taking far fewer bytes to store. Reaching the most aggressive bit widths depends on fine-tuning the latent with quantization in the loop. The results do not depend on the particular random basis, and a structured basis lets the weights be regenerated almost for free even for large networks.

Related papers

• Neural Metamorphosis [72.88137795439407]
  This paper introduces a new learning paradigm termed Neural Metamorphosis (NeuMeta), which aims to build self-morphable neural networks. NeuMeta directly learns the continuous weight manifold of neural networks. It sustains full-size performance even at a 75% compression rate.
  arXiv  Detail & Related papers  (2024-10-10T14:49:58Z)
• RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization [14.447148108341688]
  We propose efficient unsupervised domain adaptation with ReTraining-Free Quantization (RTF-Q) Our approach uses low-precision quantization architectures with varying computational costs, adapting to devices with dynamic budgets. We demonstrate that our network achieves competitive accuracy with state-of-the-art methods across three benchmarks.
  arXiv  Detail & Related papers  (2024-08-11T11:53:29Z)
• Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting [13.270381125055275]
  We propose a coarse & fine weight splitting (CFWS) method to reduce quantization error of weight. We develop an improved KL metric to determine optimal quantization scales for activation. For example, the quantized RepVGG-A1 model exhibits a mere 0.3% accuracy loss.
  arXiv  Detail & Related papers  (2023-12-17T02:31:20Z)
• Vertical Layering of Quantized Neural Networks for Heterogeneous Inference [57.42762335081385]
  We study a new vertical-layered representation of neural network weights for encapsulating all quantized models into a single one. We can theoretically achieve any precision network for on-demand service while only needing to train and maintain one model.
  arXiv  Detail & Related papers  (2022-12-10T15:57:38Z)
• Weight Fixing Networks [0.0]
  We look to whole-network quantisation to minimise the entropy and number of unique parameters in a network. We propose a new method, which we call Weight Fixing Networks (WFN) that we design to realise four model outcome objectives.
  arXiv  Detail & Related papers  (2022-10-24T19:18:02Z)
• Parameter-Efficient Masking Networks [61.43995077575439]
  Advanced network designs often contain a large number of repetitive structures (e.g., Transformer) In this study, we are the first to investigate the representative potential of fixed random weights with limited unique values by learning masks. It leads to a new paradigm for model compression to diminish the model size.
  arXiv  Detail & Related papers  (2022-10-13T03:39:03Z)
• Fast Conditional Network Compression Using Bayesian HyperNetworks [54.06346724244786]
  We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts. Our methods can quickly generate compressed networks with significantly smaller sizes than baseline methods.
  arXiv  Detail & Related papers  (2022-05-13T00:28:35Z)
• Post-training Quantization for Neural Networks with Provable Guarantees [9.58246628652846]
  We modify a post-training neural-network quantization method, GPFQ, that is based on a greedy path-following mechanism. We prove that for quantizing a single-layer network, the relative square error essentially decays linearly in the number of weights.
  arXiv  Detail & Related papers  (2022-01-26T18:47:38Z)
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time [57.52251547365967]
  We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models. We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity. Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
  arXiv  Detail & Related papers  (2021-10-08T17:03:34Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Point-Cloud Deep Learning of Porous Media for Permeability Prediction [0.0]
  We propose a novel deep learning framework for predicting permeability of porous media from their digital images. We model the boundary between solid matrix and pore spaces as point clouds and feed them as inputs to a neural network based on the PointNet architecture.
  arXiv  Detail & Related papers  (2021-07-18T22:59:21Z)

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.