Unified Scaling Laws for Compressed Representations

• URL: http://arxiv.org/abs/2506.01863v1
• Date: Mon, 02 Jun 2025 16:52:51 GMT
• Title: Unified Scaling Laws for Compressed Representations
• Authors: Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu, Vage Egiazarian, Mher Safaryan, Dan Alistarh,
• Abstract summary: We investigate whether a unified scaling framework can accurately predict model performance when training occurs over various compressed representations.<n>Our main finding is demonstrating both theoretically and empirically that there exists a simple "capacity" metric.<n>We extend our formulation to directly compare the accuracy potential of different compressed formats, and to derive better algorithms for training over sparse-quantized formats.
• Score: 69.72517034565467
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, the rise in computational cost for AI has motivated model compression techniques, notably quantization and sparsification, which have emerged to mitigate the steep computational demands associated with large-scale training and inference. This paper investigates the interplay between scaling laws and compression formats, exploring whether a unified scaling framework can accurately predict model performance when training occurs over various compressed representations, such as sparse, scalar-quantized, sparse-quantized or even vector-quantized formats. Our key contributions include validating a general scaling law formulation and showing that it is applicable both individually but also composably across compression types. Based on this, our main finding is demonstrating both theoretically and empirically that there exists a simple "capacity" metric -- based on the representation's ability to fit random Gaussian data -- which can robustly predict parameter efficiency across multiple compressed representations. On the practical side, we extend our formulation to directly compare the accuracy potential of different compressed formats, and to derive better algorithms for training over sparse-quantized formats.

Related papers

• On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization [5.952537659103525]
  We argue that many successful model compression approaches can be understood as implicitly approximating information divergences for this projection.<n>We prove convergence of iterative singular value thresholding for training neural networks subject to a soft rank constraint.
  arXiv  Detail & Related papers  (2025-07-12T23:39:14Z)
• Compression Scaling Laws:Unifying Sparsity and Quantization [65.05818215339498]
  We investigate how different compression techniques affect the scaling behavior of large language models (LLMs) during pretraining.<n>We show that weight-only quantization achieves strong parameter efficiency multipliers, while full quantization of both weights and activations shows diminishing returns at lower bitwidths.<n>Our results suggest that different compression techniques can be unified under a common scaling law framework.
  arXiv  Detail & Related papers  (2025-02-23T04:47:36Z)
• Choose Your Model Size: Any Compression by a Single Gradient Descent [9.074689052563878]
  We present Any Compression via Iterative Pruning (ACIP)<n>ACIP is an algorithmic approach to determine a compression-performance trade-off from a single gradient descent run.<n>We show that ACIP seamlessly complements common quantization-based compression techniques.
  arXiv  Detail & Related papers  (2025-02-03T18:40:58Z)
• SEE: Sememe Entanglement Encoding for Transformer-bases Models Compression [20.824040486029354]
  Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are high, limiting their application in resource-constrained scenarios.<n>An effective approach is to eliminate redundant model parameters and computational costs while incorporating efficient expert-derived knowledge structures to achieve a balance between compression and performance.
  arXiv  Detail & Related papers  (2024-12-15T12:01:43Z)
• Observational Scaling Laws and the Predictability of Language Model Performance [51.2336010244645]
  We propose an observational approach that bypasses model training and instead builds scaling laws from 100 publically available models. We show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models. We show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.
  arXiv  Detail & Related papers  (2024-05-17T17:49:44Z)
• Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models [9.91972450276408]
  This paper introduces an innovative approach for the parametric and practical compression of Large Language Models (LLMs) based on reduced order modelling. Our method represents a significant advancement in model compression by leveraging matrix decomposition, demonstrating superior efficacy compared to the prevailing state-of-the-art structured pruning method.
  arXiv  Detail & Related papers  (2023-12-12T07:56:57Z)
• Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression [151.3826781154146]
  latent variables with priors and hyperpriors is an essential problem in variational image compression. We find inter-correlations and intra-correlations exist when observing latent variables in a vectorized perspective. Our model has better rate-distortion performance and an impressive $3.18times$ compression speed up.
  arXiv  Detail & Related papers  (2022-03-21T11:44:17Z)
• Post-Training Quantization for Cross-Platform Learned Image Compression [15.67527732099067]
  It has been witnessed that learned image compression has outperformed conventional image coding techniques. One of the most critical issues that need to be considered is the non-deterministic calculation. We propose to solve this problem by introducing well-developed post-training quantization.
  arXiv  Detail & Related papers  (2022-02-15T15:41:12Z)
• Real-Time Regression with Dividing Local Gaussian Processes [62.01822866877782]
  Local Gaussian processes are a novel, computationally efficient modeling approach based on Gaussian process regression. Due to an iterative, data-driven division of the input space, they achieve a sublinear computational complexity in the total number of training points in practice. A numerical evaluation on real-world data sets shows their advantages over other state-of-the-art methods in terms of accuracy as well as prediction and update speed.
  arXiv  Detail & Related papers  (2020-06-16T18:43:31Z)
• Compressing Large Sample Data for Discriminant Analysis [78.12073412066698]
  We consider the computational issues due to large sample size within the discriminant analysis framework. We propose a new compression approach for reducing the number of training samples for linear and quadratic discriminant analysis.
  arXiv  Detail & Related papers  (2020-05-08T05:09:08Z)

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.