SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale

• URL: http://arxiv.org/abs/2512.10922v1
• Date: Thu, 11 Dec 2025 18:47:48 GMT
• Title: SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale
• Authors: Max Zimmer, Christophe Roux, Moritz Wagner, Deborah Hendrych, Sebastian Pokutta,
• Abstract summary: We propose a tractable and simple 1-swap algorithm that warms starts from any pruning mask and runs efficiently at LLM scale.<n>We demonstrate that our approach reduces per-layer pruning error by up to 60% over Wanda (Sun et al., 2023) and consistently improves perplexity and zero-shot accuracy across state-of-the-art GPT architectures.
• Score: 22.25809500403244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The resource requirements of Neural Networks can be significantly reduced through pruning -- the removal of seemingly less important parameters. However, with the rise of Large Language Models (LLMs), full retraining to recover pruning-induced performance degradation is often prohibitive and classical approaches such as global magnitude pruning are suboptimal on Transformer architectures. State-of-the-art methods hence solve a layer-wise mask selection problem, the problem of finding a pruning mask which minimizes the per-layer pruning error on a small set of calibration data. Exactly solving this problem to optimality using Integer Programming (IP) solvers is computationally infeasible due to its combinatorial nature and the size of the search space, and existing approaches therefore rely on approximations or heuristics. In this work, we demonstrate that the mask selection problem can be made drastically more tractable at LLM scale. To that end, we decouple the rows by enforcing equal sparsity levels per row. This allows us to derive optimal 1-swaps (exchanging one kept and one pruned weight) that can be computed efficiently using the Gram matrix of the calibration data. Using these observations, we propose a tractable and simple 1-swap algorithm that warm starts from any pruning mask, runs efficiently on GPUs at LLM scale, and is essentially hyperparameter-free. We demonstrate that our approach reduces per-layer pruning error by up to 60% over Wanda (Sun et al., 2023) and consistently improves perplexity and zero-shot accuracy across state-of-the-art GPT architectures.

Related papers

• Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe [61.68406997155879]
  State-of-the-art Large Language Model (LLM) pruning methods operate layer-wise, minimizing the per-layer pruning error on a small dataset to avoid full retraining.<n>Existing methods hence rely on greedy convexs that ignore the weight interactions in the pruning objective.<n>Our method drastically reduces the per-layer pruning error, outperforms strong baselines on state-of-the-art GPT architectures, and remains memory-efficient.
  arXiv  Detail & Related papers  (2025-10-15T16:13:44Z)
• High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution [87.56382172827526]
  High-frequency regions are most critical for reconstruction.<n>We propose a training-free adaptive masking module for acceleration.<n>Our method reduces FLOPs by 24--43% for state-of-the-art models.
  arXiv  Detail & Related papers  (2025-05-11T13:18:03Z)
• Deep-ICE: The first globally optimal algorithm for empirical risk minimization of two-layer maxout and ReLU networks [1.7266553199919665]
  This paper introduces the first globally optimal algorithm for the empirical risk problem of two-layer maxout and ReLU networks.<n>The proposed algorithm provides provably exact solutions for small-scale datasets.<n>To handle larger datasets, we introduce a novel coreset selection method that reduces the data size to a manageable scale.
  arXiv  Detail & Related papers  (2025-05-09T02:34:54Z)
• Pushing the Limits of Large Language Model Quantization via the Linearity Theorem [71.3332971315821]
  We present a "line theoremarity" establishing a direct relationship between the layer-wise $ell$ reconstruction error and the model perplexity increase due to quantization. This insight enables two novel applications: (1) a simple data-free LLM quantization method using Hadamard rotations and MSE-optimal grids, dubbed HIGGS, and (2) an optimal solution to the problem of finding non-uniform per-layer quantization levels.
  arXiv  Detail & Related papers  (2024-11-26T15:35:44Z)
• HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization [55.972018549438964]
  Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy.<n>We propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable fine-tuning of LLMs in heterogeneous environments.<n> Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.
  arXiv  Detail & Related papers  (2024-11-10T19:59:54Z)
• Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization [0.0]
  We present Double Sparse Factorization (DSF), where we factorize each weight matrix into two sparse matrices.<n>Our method achieves state-of-the-art results, enabling unprecedented sparsification of neural networks.
  arXiv  Detail & Related papers  (2024-09-27T15:48:39Z)
• ADMM Based Semi-Structured Pattern Pruning Framework For Transformer [4.02487511510606]
  This paper introduces Alternating Direction Method of Multipliers(ADMM) based pattern pruning framework to reshape the distribution of activation map. We conduct extensive experiments on classification tasks over GLUE dataset. We achieve 50% percent compression ratio while maintaining overall score 80.1 on GLUE dataset.
  arXiv  Detail & Related papers  (2024-07-11T09:35:08Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning that learns the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model.<n>We achieve this by learning an underlying Bernoulli distribution to sample binary pruning masks.<n>Experiments conducted on LLaMA, LLaMA-2, LLaMA-3, Vicuna, and Mistral models demonstrate the promising performance of our method in efficiency and effectiveness.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Smooth Bilevel Programming for Sparse Regularization [5.177947445379688]
  Iteratively reweighted least square (IRLS) is a popular approach to solve sparsity-enforcing regression problems in machine learning. We show how a surprisingly reparametrization of IRLS, coupled with a bilevel scheme, achieves topranging of sparsity.
  arXiv  Detail & Related papers  (2021-06-02T19:18:22Z)
• Layer-adaptive sparsity for the Magnitude-based Pruning [88.37510230946478]
  We propose a novel importance score for global pruning, coined layer-adaptive magnitude-based pruning (LAMP) score. LAMP consistently outperforms popular existing schemes for layerwise sparsity selection.
  arXiv  Detail & Related papers  (2020-10-15T09:14:02Z)

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.