Structured Pruning of Neural Networks for Constraints Learning

• URL: http://arxiv.org/abs/2307.07457v1
• Date: Fri, 14 Jul 2023 16:36:49 GMT
• Title: Structured Pruning of Neural Networks for Constraints Learning
• Authors: Matteo Cacciola and Antonio Frangioni and Andrea Lodi
• Abstract summary: We show the effectiveness of pruning, one of these techniques, when applied to ANNs prior to their integration into MIPs. We conduct experiments using feed-forward neural networks with multiple layers to construct adversarial examples. Our results demonstrate that pruning offers remarkable reductions in solution times without hindering the quality of the final decision.
• Score: 5.689013857168641
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, the integration of Machine Learning (ML) models with Operation Research (OR) tools has gained popularity across diverse applications, including cancer treatment, algorithmic configuration, and chemical process optimization. In this domain, the combination of ML and OR often relies on representing the ML model output using Mixed Integer Programming (MIP) formulations. Numerous studies in the literature have developed such formulations for many ML predictors, with a particular emphasis on Artificial Neural Networks (ANNs) due to their significant interest in many applications. However, ANNs frequently contain a large number of parameters, resulting in MIP formulations that are impractical to solve, thereby impeding scalability. In fact, the ML community has already introduced several techniques to reduce the parameter count of ANNs without compromising their performance, since the substantial size of modern ANNs presents challenges for ML applications as it significantly impacts computational efforts during training and necessitates significant memory resources for storage. In this paper, we showcase the effectiveness of pruning, one of these techniques, when applied to ANNs prior to their integration into MIPs. By pruning the ANN, we achieve significant improvements in the speed of the solution process. We discuss why pruning is more suitable in this context compared to other ML compression techniques, and we identify the most appropriate pruning strategies. To highlight the potential of this approach, we conduct experiments using feed-forward neural networks with multiple layers to construct adversarial examples. Our results demonstrate that pruning offers remarkable reductions in solution times without hindering the quality of the final decision, enabling the resolution of previously unsolvable instances.

Related papers

• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Common pitfalls to avoid while using multiobjective optimization in machine learning [1.2499537119440245]
  There has been an increasing interest in exploring the application of multiobjective optimization (MOO) in machine learning (ML) Despite its potential, there is a noticeable lack of satisfactory literature that could serve as an entry-level guide for ML practitioners who want to use MOO. We critically review previous studies, particularly those involving MOO in deep learning (using Physics-Informed Neural Networks (PINNs) as a guiding example) and identify misconceptions that highlight the need for a better grasp of MOO principles in ML.
  arXiv  Detail & Related papers  (2024-05-02T17:12:25Z)
• Deep learning enhanced mixed integer optimization: Learning to reduce model dimensionality [0.0]
  This work introduces a framework to address the computational complexity inherent in Mixed-Integer Programming. By employing deep learning, we construct problem-specific models that identify and exploit common structures across MIP instances. We present an algorithm for generating synthetic data enhancing the robustness and generalizability of our models.
  arXiv  Detail & Related papers  (2024-01-17T19:15:13Z)
• Machine Learning Insides OptVerse AI Solver: Design Principles and Applications [74.67495900436728]
  We present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI solver. We showcase our methods for generating complex SAT and MILP instances utilizing generative models that mirror multifaceted structures of real-world problem. We detail the incorporation of state-of-the-art parameter tuning algorithms which markedly elevate solver performance.
  arXiv  Detail & Related papers  (2024-01-11T15:02:15Z)
• Computational Tradeoffs of Optimization-Based Bound Tightening in ReLU Networks [4.01907644010256]
  Mixed-Integer Linear Programming (MILP) models to represent neural networks with Rectified Linear Unit (ReLU) activations has become increasingly widespread in the last decade. This has enabled the use of MILP technology to test-or stress-their behavior, to adversarially improve their training, and to embed them in optimization models leveraging their predictive power. We provide guidelines for implementing these models based on the impact of network structure, regularization, and rounding.
  arXiv  Detail & Related papers  (2023-12-27T19:32:59Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics [77.34726150561087]
  Recent developments in artificial neural networks, particularly deep learning (DL), are reviewed in detail. Both hybrid and pure machine learning (ML) methods are discussed. History and limitations of AI are recounted and discussed, with particular attention at pointing out misstatements or misconceptions of the classics.
  arXiv  Detail & Related papers  (2022-12-18T02:03:00Z)
• Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers [67.688697838109]
  This paper presents a novel method to train quantized RNNLMs from scratch using alternating direction methods of multipliers (ADMM) Experiments on two tasks suggest the proposed ADMM quantization achieved a model size compression factor of up to 31 times over the full precision baseline RNNLMs.
  arXiv  Detail & Related papers  (2021-11-29T09:30:06Z)
• A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks [2.7393821783237184]
  Model Compression and Acceleration (MCA) techniques are used to transform large pre-trained networks into smaller models. We propose a clustering-based approach that is able to increase the number of employed centroids/representatives. This is achieved by imposing a special structure to the employed representatives, which is enabled by the particularities of the problem at hand.
  arXiv  Detail & Related papers  (2021-07-19T18:22:07Z)
• Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning [5.490618192331097]
  We consider a model-agnostic solution to the problem of Multi-Domain Learning for multi-modal applications. Our method is model-agnostic, requiring no additional model parameters and no network architecture changes. We demonstrate our solution to a fitting problem in medical imaging, specifically, in the automatic segmentation of white matter hyperintensity.
  arXiv  Detail & Related papers  (2021-02-25T19:54:44Z)
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference [56.24109486973292]
  We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
  arXiv  Detail & Related papers  (2021-02-22T19:00:05Z)

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.