Weight Variance Amplifier Improves Accuracy in High-Sparsity One-Shot Pruning

• URL: http://arxiv.org/abs/2511.14282v1
• Date: Tue, 18 Nov 2025 09:18:26 GMT
• Title: Weight Variance Amplifier Improves Accuracy in High-Sparsity One-Shot Pruning
• Authors: Vincent-Daniel Yun, Junhyuk Jo, Sunwoo Lee,
• Abstract summary: One-shot pruning is an effective strategy for reducing model size without additional training.<n>We propose a Variance Amplifying Regularizer ( VAR) that deliberately increases the variance of model parameters during training.
• Score: 2.0541440514363365
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Deep neural networks achieve outstanding performance in visual recognition tasks, yet their large number of parameters makes them less practical for real-world applications. Recently, one-shot pruning has emerged as an effective strategy for reducing model size without additional training. However, models trained with standard objective functions often suffer a significant drop in accuracy after aggressive pruning. Some existing pruning-robust optimizers, such as SAM, and CrAM, mitigate this accuracy drop by guiding the model toward flatter regions of the parameter space, but they inevitably incur non-negligible additional computations. We propose a Variance Amplifying Regularizer (VAR) that deliberately increases the variance of model parameters during training. Our study reveals an intriguing finding that parameters with higher variance exhibit greater pruning robustness. VAR exploits this property by promoting such variance in the weight distribution, thereby mitigating the adverse effects of pruning. We further provide a theoretical analysis of its convergence behavior, supported by extensive empirical results demonstrating the superior pruning robustness of VAR.

Related papers

• Sparsity Induction for Accurate Post-Training Pruning of Large Language Models [23.002927923453118]
  Post-training sparsity (PTS) reduces model cost by removing weights from dense networks.<n>But native dense matrices lack high sparsity, making existing approaches that directly remove weights disrupt model states.<n>We propose Sparsity Induction, which promotes models toward higher sparsity at both distribution and feature levels before pruning.
  arXiv  Detail & Related papers  (2026-02-25T07:25:01Z)
• Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog [72.4168434368873]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources.<n>We propose a gradual compacting method that divides the compression process into multiple fine-grained iterations.<n>This iterative approach-reminiscent of the "boiling frog" effect-enables the model to be progressively compressed without abrupt performance loss.
  arXiv  Detail & Related papers  (2026-02-04T06:56:52Z)
• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• Training Discrete Deep Generative Models via Gapped Straight-Through Estimator [72.71398034617607]
  We propose a Gapped Straight-Through ( GST) estimator to reduce the variance without incurring resampling overhead. This estimator is inspired by the essential properties of Straight-Through Gumbel-Softmax. Experiments demonstrate that the proposed GST estimator enjoys better performance compared to strong baselines on two discrete deep generative modeling tasks.
  arXiv  Detail & Related papers  (2022-06-15T01:46:05Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks [38.153825455980645]
  Recent empirical evidence indicates that the practice of overization not only benefits training large models, but also assists - perhaps counterintuitively - building lightweight models. This paper sheds light on these empirical findings by theoretically characterizing the high-dimensional toolsets of model pruning. We analytically identify regimes in which, even if the location of the most informative features is known, we are better off fitting a large model and then pruning.
  arXiv  Detail & Related papers  (2020-12-16T05:13:30Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness [3.039568795810294]
  This paper first investigates the robustness of pruned models with different compression ratios under the gradual pruning process. We then test the performance of mixing the clean data and adversarial examples into the gradual pruning process, called adversarial pruning. To better balance the AER, we propose an approach called blind adversarial pruning (BAP), which introduces the idea of blind adversarial training into the gradual pruning process.
  arXiv  Detail & Related papers  (2020-04-10T02:27:48Z)
• Learnable Bernoulli Dropout for Bayesian Deep Learning [53.79615543862426]
  Learnable Bernoulli dropout (LBD) is a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. LBD leads to improved accuracy and uncertainty estimates in image classification and semantic segmentation.
  arXiv  Detail & Related papers  (2020-02-12T18:57:14Z)

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.