Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging

• URL: http://arxiv.org/abs/2306.16788v3
• Date: Sat, 23 Mar 2024 07:05:26 GMT
• Title: Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
• Authors: Max Zimmer, Christoph Spiegel, Sebastian Pokutta,
• Abstract summary: We introduce Sparse Model Soups (SMS), a novel method for merging sparse models by initiating each prune-retrain cycle with the averaged model from the previous phase. SMS preserves sparsity, exploits sparse network benefits, is modular and fully parallelizable, and substantially improves IMP's performance.
• Score: 24.64264715041198
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks can be significantly compressed by pruning, yielding sparse models with reduced storage and computational demands while preserving predictive performance. Model soups (Wortsman et al., 2022) enhance generalization and out-of-distribution (OOD) performance by averaging the parameters of multiple models into a single one, without increasing inference time. However, achieving both sparsity and parameter averaging is challenging as averaging arbitrary sparse models reduces the overall sparsity due to differing sparse connectivities. This work addresses these challenges by demonstrating that exploring a single retraining phase of Iterative Magnitude Pruning (IMP) with varied hyperparameter configurations such as batch ordering or weight decay yields models suitable for averaging, sharing identical sparse connectivity by design. Averaging these models significantly enhances generalization and OOD performance over their individual counterparts. Building on this, we introduce Sparse Model Soups (SMS), a novel method for merging sparse models by initiating each prune-retrain cycle with the averaged model from the previous phase. SMS preserves sparsity, exploits sparse network benefits, is modular and fully parallelizable, and substantially improves IMP's performance. We further demonstrate that SMS can be adapted to enhance state-of-the-art pruning-during-training approaches.

Related papers

• Pruning Large Language Models with Semi-Structural Adaptive Sparse Training [17.381160429641316]
  We propose a pruning pipeline for semi-structured sparse models via retraining, termed Adaptive Sparse Trainer (AST) AST transforms dense models into sparse ones by applying decay to masked weights while allowing the model to adaptively select masks throughout the training process. Our work demonstrates the feasibility of deploying semi-structured sparse large language models and introduces a novel method for achieving highly compressed models.
  arXiv  Detail & Related papers  (2024-07-30T06:33:44Z)
• Bayesian vs. PAC-Bayesian Deep Neural Network Ensembles [7.883369697332076]
  We argue that neither the sampling nor the weighting in a Bayes ensemble are particularly well-suited for increasing generalization performance. We show that state-of-the-art Bayes ensembles from the literature, despite being computationally demanding, do not improve over simple uniformly weighted deep ensembles.
  arXiv  Detail & Related papers  (2024-06-08T13:19:18Z)
• WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average [21.029085451757368]
  Weight averaging methods aim at balancing the generalization of ensembling and the inference speed of a single model. We introduce WASH, a novel distributed method for training model ensembles for weight averaging that achieves state-of-the-art image classification accuracy.
  arXiv  Detail & Related papers  (2024-05-27T09:02:57Z)
• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution [67.9215891673174]
  We propose score entropy as a novel loss that naturally extends score matching to discrete spaces. We test our Score Entropy Discrete Diffusion models on standard language modeling tasks.
  arXiv  Detail & Related papers  (2023-10-25T17:59:12Z)
• Improving Transferability of Adversarial Examples via Bayesian Attacks [84.90830931076901]
  We introduce a novel extension by incorporating the Bayesian formulation into the model input as well, enabling the joint diversification of both the model input and model parameters. Our method achieves a new state-of-the-art on transfer-based attacks, improving the average success rate on ImageNet and CIFAR-10 by 19.14% and 2.08%, respectively.
  arXiv  Detail & Related papers  (2023-07-21T03:43:07Z)
• Maintaining Stability and Plasticity for Predictive Churn Reduction [8.971668467496055]
  We propose a solution called Accumulated Model Combination (AMC) AMC is a general technique and we propose several instances of it, each having their own advantages depending on the model and data properties.
  arXiv  Detail & Related papers  (2023-05-06T20:56:20Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• Dynamic Model Pruning with Feedback [64.019079257231]
  We propose a novel model compression method that generates a sparse trained model without additional overhead. We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models.
  arXiv  Detail & Related papers  (2020-06-12T15:07:08Z)
• Normalizing Flows with Multi-Scale Autoregressive Priors [131.895570212956]
  We introduce channel-wise dependencies in their latent space through multi-scale autoregressive priors (mAR) Our mAR prior for models with split coupling flow layers (mAR-SCF) can better capture dependencies in complex multimodal data. We show that mAR-SCF allows for improved image generation quality, with gains in FID and Inception scores compared to state-of-the-art flow-based models.
  arXiv  Detail & Related papers  (2020-04-08T09:07:11Z)

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.