Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning

• URL: http://arxiv.org/abs/2305.14852v2
• Date: Fri, 26 Apr 2024 05:50:29 GMT
• Title: Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
• Authors: Moonseok Choi, Hyungi Lee, Giung Nam, Juho Lee,
• Abstract summary: Iterative Magnitude Pruning (IMP) still stands as a state-of-the-art algorithm despite its simple nature, particularly in extremely sparse regimes. We propose Sparse Weight Averaging with Multiple Particles (SWAMP), a straightforward modification of IMP that achieves performance comparable to an ensemble of two IMP solutions.
• Score: 16.869553861212548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the ever-increasing size of modern neural networks, the significance of sparse architectures has surged due to their accelerated inference speeds and minimal memory demands. When it comes to global pruning techniques, Iterative Magnitude Pruning (IMP) still stands as a state-of-the-art algorithm despite its simple nature, particularly in extremely sparse regimes. In light of the recent finding that the two successive matching IMP solutions are linearly connected without a loss barrier, we propose Sparse Weight Averaging with Multiple Particles (SWAMP), a straightforward modification of IMP that achieves performance comparable to an ensemble of two IMP solutions. For every iteration, we concurrently train multiple sparse models, referred to as particles, using different batch orders yet the same matching ticket, and then weight average such models to produce a single mask. We demonstrate that our method consistently outperforms existing baselines across different sparsities through extensive experiments on various data and neural network structures.

Related papers

• 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)
• Parallel-in-Time Solutions with Random Projection Neural Networks [0.07282584715927627]
  This paper considers one of the fundamental parallel-in-time methods for the solution of ordinary differential equations, Parareal, and extends it by adopting a neural network as a coarse propagator. We provide a theoretical analysis of the convergence properties of the proposed algorithm and show its effectiveness for several examples, including Lorenz and Burgers' equations.
  arXiv  Detail & Related papers  (2024-08-19T07:32:41Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• A DeepParticle method for learning and generating aggregation patterns in multi-dimensional Keller-Segel chemotaxis systems [3.6184545598911724]
  We study a regularized interacting particle method for computing aggregation patterns and near singular solutions of a Keller-Segal (KS) chemotaxis system in two and three space dimensions. We further develop DeepParticle (DP) method to learn and generate solutions under variations of physical parameters.
  arXiv  Detail & Related papers  (2022-08-31T20:52:01Z)
• Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods [35.24886589614034]
  We consider quadratic definite Ising models on the hypercube with a general interaction $J$. Our general result implies the first time sampling algorithms for low-rank Ising models.
  arXiv  Detail & Related papers  (2022-02-17T21:43:50Z)
• Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities [80.06422693778141]
  We propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, kernels, filters/feature maps) We refer to this algorithm as Dynamic Probabilistic Pruning (DPP) We show that DPP achieves competitive compression rates and classification accuracy when pruning common deep learning models trained on different benchmark datasets for image classification.
  arXiv  Detail & Related papers  (2021-05-26T17:01:52Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Learning Sparse Filters in Deep Convolutional Neural Networks with a l1/l2 Pseudo-Norm [5.3791844634527495]
  Deep neural networks (DNNs) have proven to be efficient for numerous tasks, but come at a high memory and computation cost. Recent research has shown that their structure can be more compact without compromising their performance. We present a sparsity-inducing regularization term based on the ratio l1/l2 pseudo-norm defined on the filter coefficients.
  arXiv  Detail & Related papers  (2020-07-20T11:56:12Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)
• Rethinking Differentiable Search for Mixed-Precision Neural Networks [83.55785779504868]
  Low-precision networks with weights and activations quantized to low bit-width are widely used to accelerate inference on edge devices. Current solutions are uniform, using identical bit-width for all filters. This fails to account for the different sensitivities of different filters and is suboptimal. Mixed-precision networks address this problem, by tuning the bit-width to individual filter requirements.
  arXiv  Detail & Related papers  (2020-04-13T07:02:23Z)

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.