A Unified Framework for Soft Threshold Pruning

• URL: http://arxiv.org/abs/2302.13019v1
• Date: Sat, 25 Feb 2023 08:16:14 GMT
• Title: A Unified Framework for Soft Threshold Pruning
• Authors: Yanqi Chen, Zhengyu Ma, Wei Fang, Xiawu Zheng, Zhaofei Yu, Yonghong Tian
• Abstract summary: We reformulate soft threshold pruning as an implicit optimization problem solved using the Iterative Shrinkage-Thresholding Algorithm (ISTA) We derive an optimal threshold scheduler through an in-depth study of threshold scheduling based on our framework. In principle, the derived pruning algorithm could sparsify any mathematical model trained via SGD.
• Score: 27.853698217792456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Soft threshold pruning is among the cutting-edge pruning methods with state-of-the-art performance. However, previous methods either perform aimless searching on the threshold scheduler or simply set the threshold trainable, lacking theoretical explanation from a unified perspective. In this work, we reformulate soft threshold pruning as an implicit optimization problem solved using the Iterative Shrinkage-Thresholding Algorithm (ISTA), a classic method from the fields of sparse recovery and compressed sensing. Under this theoretical framework, all threshold tuning strategies proposed in previous studies of soft threshold pruning are concluded as different styles of tuning $L_1$-regularization term. We further derive an optimal threshold scheduler through an in-depth study of threshold scheduling based on our framework. This scheduler keeps $L_1$-regularization coefficient stable, implying a time-invariant objective function from the perspective of optimization. In principle, the derived pruning algorithm could sparsify any mathematical model trained via SGD. We conduct extensive experiments and verify its state-of-the-art performance on both Artificial Neural Networks (ResNet-50 and MobileNet-V1) and Spiking Neural Networks (SEW ResNet-18) on ImageNet datasets. On the basis of this framework, we derive a family of pruning methods, including sparsify-during-training, early pruning, and pruning at initialization. The code is available at https://github.com/Yanqi-Chen/LATS.

Related papers

• Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training [3.195234044113248]
  We exploit functional information from dense pre-trained models to obtain sparse models that maximize the activations' alignment w.r.t. We propose textscNeuroAl, a emphtop-up algorithm that modifies the block-wise and row-wise sparsity ratios to maximize the emphneuron alignment among activations. We test our method on 4 different LLM families and 3 different sparsity ratios, showing how it consistently outperforms the latest state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-11-11T15:30:16Z)
• Concurrent Training and Layer Pruning of Deep Neural Networks [0.0]
  We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. We employ a structure using residual connections around nonlinear network sections that allow the flow of information through the network once a nonlinear section is pruned.
  arXiv  Detail & Related papers  (2024-06-06T23:19:57Z)
• FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning [17.60353530072587]
  Network pruning offers a solution to reduce model size and computational cost while maintaining performance. Most current pruning methods focus primarily on improving sparsity by reducing the number of nonzero parameters. We propose FALCON, a novel-optimization-based framework for network pruning that jointly takes into account model accuracy (fidelity), FLOPs, and sparsity constraints.
  arXiv  Detail & Related papers  (2024-03-11T18:40:47Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients [36.078414964088196]
  Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network. Current methods are insufficient to enable this optimization and lead to a large degradation in model performance. We propose Prospect Pruning (ProsPr), which uses meta-gradients through the first few steps of optimization to determine which weights to prune. Our method achieves state-of-the-art pruning performance on a variety of vision classification tasks, with less data and in a single shot compared to existing pruning-at-initialization methods.
  arXiv  Detail & Related papers  (2022-02-16T15:18:55Z)
• COPS: Controlled Pruning Before Training Starts [68.8204255655161]
  State-of-the-art deep neural network (DNN) pruning techniques, applied one-shot before training starts, evaluate sparse architectures with the help of a single criterion -- called pruning score. In this work we do not concentrate on a single pruning criterion, but provide a framework for combining arbitrary GSSs to create more powerful pruning strategies.
  arXiv  Detail & Related papers  (2021-07-27T08:48:01Z)
• Only Train Once: A One-Shot Neural Network Training And Pruning Framework [31.959625731943675]
  Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices. We propose a framework that DNNs are slimmer with competitive performances and significant FLOPs reductions by Only-Train-Once (OTO) OTO contains two keys: (i) we partition the parameters of DNNs into zero-invariant groups, enabling us to prune zero groups without affecting the output; and (ii) to promote zero groups, we then formulate a structured-Image optimization algorithm, Half-Space Projected (HSPG) To demonstrate the effectiveness of OTO, we train and
  arXiv  Detail & Related papers  (2021-07-15T17:15:20Z)
• Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition [161.09660864941603]
  We improve the scalability of Branch and Bound (BaB) algorithms for formally proving input-output properties of neural networks. We present a novel activation-based branching strategy and a BaB framework, named Branch and Dual Network Bound (BaDNB) BaDNB outperforms previous complete verification systems by a large margin, cutting average verification times by factors up to 50 on adversarial properties.
  arXiv  Detail & Related papers  (2021-04-14T09:22:42Z)
• 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)

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.