Soft Threshold Weight Reparameterization for Learnable Sparsity

• URL: http://arxiv.org/abs/2002.03231v9
• Date: Mon, 22 Jun 2020 23:37:12 GMT
• Title: Soft Threshold Weight Reparameterization for Learnable Sparsity
• Abstract summary: We propose STR, a novel use of the soft-threshold operator on inference weights. STR smoothly induces sparsity while learning pruning thresholds thereby obtaining a non-uniform sparsity budget. Our method achieves state-of-the-art accuracy for unstructured sparsity in CNNs (ResNet50 and MobileNetV1 on ImageNet-1K) and, additionally, learns non-uniform budgets that empirically reduce the FLOPs by up to 50%.
• Score: 46.419079691593396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have sub-optimal layer-wise parameter allocation resulting in a) lower prediction accuracy or b) higher inference cost (FLOPs). This work proposes Soft Threshold Reparameterization (STR), a novel use of the soft-threshold operator on DNN weights. STR smoothly induces sparsity while learning pruning thresholds thereby obtaining a non-uniform sparsity budget. Our method achieves state-of-the-art accuracy for unstructured sparsity in CNNs (ResNet50 and MobileNetV1 on ImageNet-1K), and, additionally, learns non-uniform budgets that empirically reduce the FLOPs by up to 50%. Notably, STR boosts the accuracy over existing results by up to 10% in the ultra sparse (99%) regime and can also be used to induce low-rank (structured sparsity) in RNNs. In short, STR is a simple mechanism which learns effective sparsity budgets that contrast with popular heuristics. Code, pretrained models and sparsity budgets are at https://github.com/RAIVNLab/STR.

Related papers

• Diffusion-Based Generative Priors for Efficient Beam Alignment in Directional Networks [2.1326442458534403]
  Beam alignment is a key challenge in directional mmWave and THz systems, where narrow beams require accurate yet low-overhead training.<n>We recast beam alignment as a generative task and propose a conditional diffusion model that learns a probabilistic beam prior to compact geometric and multipath features.
  arXiv  Detail & Related papers  (2026-03-30T09:21:03Z)
• Provably robust learning of regression neural networks using $β$-divergences [1.2891210250935143]
  Existing robust training methods for regression neural networks (NNs) are often limited in scope and rely primarily on empirical validation.<n>We propose a new robust learning framework for regression NNs based on the $$-divergence (also known as the density power divergence) which we call rRNet'<n>We prove that rRNet attains the optimal 50% breakdown point at the assumed model for all $in(0, 1]$, providing a strong global robustness guarantee.
  arXiv  Detail & Related papers  (2026-02-09T17:32:43Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• NIRVANA: Structured pruning reimagined for large language models compression [50.651730342011014]
  We introduce NIRVANA, a novel pruning method designed to balance immediate zero-shot preservation accuracy with robust fine-tuning.<n>To further address the unique challenges posed by structured pruning, NIRVANA incorporates an adaptive sparsity allocation mechanism across layers and modules.<n>Experiments conducted on Llama3, Qwen, T5 models demonstrate that NIRVANA outperforms existing structured pruning methods under equivalent sparsity constraints.
  arXiv  Detail & Related papers  (2025-09-17T17:59:00Z)
• Explainable Bayesian deep learning through input-skip Latent Binary Bayesian Neural Networks [11.815986153374967]
  This article advances LBBNNs by enabling covariates to skip to any succeeding layer or be excluded. The input-skip LBBNN approach reduces network density significantly compared to standard LBBNNs, achieving over 99% reduction for small networks and over 99.9% for larger ones. For example, on MNIST, we reached 97% accuracy and great calibration with just 935 weights, reaching state-of-the-art for compression of neural networks.
  arXiv  Detail & Related papers  (2025-03-13T15:59:03Z)
• AUTOSPARSE: Towards Automated Sparse Training of Deep Neural Networks [2.6742343015805083]
  We propose Gradient Annealing (GA) to explore the non-uniform distribution of sparsity inherent within neural networks. GA provides an elegant trade-off between sparsity and accuracy without the need for additional sparsity-inducing regularization. We integrate GA with the latest learnable pruning methods to create an automated sparse training algorithm called AutoSparse.
  arXiv  Detail & Related papers  (2023-04-14T06:19:07Z)
• Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off [19.230329532065635]
  Sparse training could significantly mitigate the training costs by reducing the model size. Existing sparse training methods mainly use either random-based or greedy-based drop-and-grow strategies. In this work, we consider the dynamic sparse training as a sparse connectivity search problem. Experimental results show that sparse models (up to 98% sparsity) obtained by our proposed method outperform the SOTA sparse training methods.
  arXiv  Detail & Related papers  (2022-11-30T01:22:25Z)
• Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask [8.02992650002693]
  We study and evaluate various training recipes for N:M sparsity in terms of the trade-off between model accuracy and compute cost. We propose two new decay-based pruning methods, namely "pruning mask decay" and "sparse structure decay" Our evaluations indicate that these proposed methods consistently deliver state-of-the-art (SOTA) model accuracy, comparable to unstructured sparsity.
  arXiv  Detail & Related papers  (2022-09-15T21:30:55Z)
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks [146.2011175973769]
  This paper proposes Efficient Sharpness Aware Minimizer (M) which boosts SAM s efficiency at no cost to its generalization performance. M includes two novel and efficient training strategies-StochasticWeight Perturbation and Sharpness-Sensitive Data Selection. We show, via extensive experiments on the CIFAR and ImageNet datasets, that ESAM enhances the efficiency over SAM from requiring 100% extra computations to 40% vis-a-vis bases.
  arXiv  Detail & Related papers  (2021-10-07T02:20:37Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch [75.69506249886622]
  Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. In this paper, we are the first to study training from scratch an N:M fine-grained structured sparse network.
  arXiv  Detail & Related papers  (2021-02-08T05:55:47Z)
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning [90.44219200633286]
  We propose a simple yet very effective adversarial fine-tuning approach based on a $textitslow start, fast decay$ learning rate scheduling strategy. Experimental results show that the proposed adversarial fine-tuning approach outperforms the state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-12-25T20:50:15Z)
• Holistic Filter Pruning for Efficient Deep Neural Networks [25.328005340524825]
  "Holistic Filter Pruning" (HFP) is a novel approach for common DNN training that is easy to implement and enables to specify accurate pruning rates. In various experiments, we give insights into the training and achieve state-of-the-art performance on CIFAR-10 and ImageNet.
  arXiv  Detail & Related papers  (2020-09-17T09:23:36Z)
• TRP: Trained Rank Pruning for Efficient Deep Neural Networks [69.06699632822514]
  We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. A nuclear regularization optimized by sub-gradient descent is utilized to further promote low rank in TRP. The TRP trained network inherently has a low-rank structure, and is approximated with negligible performance loss.
  arXiv  Detail & Related papers  (2020-04-30T03:37:36Z)
• Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets [13.102014808597264]
  This paper focuses on a co-design of efficient compression algorithms and sparse neural architectures for robust and accurate deep learning. We leverage the relaxed augmented Lagrangian based algorithms to prune the weights of adversarially trained DNNs. Using a Feynman-Kac formalism principled robust and sparse DNNs, we can at least double the channel sparsity of the adversarially trained ResNet20 for CIFAR10 classification.
  arXiv  Detail & Related papers  (2020-03-02T02:18:43Z)

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.