A New PHO-rmula for Improved Performance of Semi-Structured Networks

• URL: http://arxiv.org/abs/2306.00522v1
• Date: Thu, 1 Jun 2023 10:23:28 GMT
• Title: A New PHO-rmula for Improved Performance of Semi-Structured Networks
• Authors: David R\"ugamer
• Abstract summary: We show that techniques to properly identify the contributions of the different model components in SSNs lead to suboptimal network estimation. We propose a non-invasive post-hocization (PHO) that guarantees identifiability of model components and provides better estimation and prediction quality. Our theoretical findings are supported by numerical experiments, a benchmark comparison as well as a real-world application to COVID-19 infections.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances to combine structured regression models and deep neural networks for better interpretability, more expressiveness, and statistically valid uncertainty quantification demonstrate the versatility of semi-structured neural networks (SSNs). We show that techniques to properly identify the contributions of the different model components in SSNs, however, lead to suboptimal network estimation, slower convergence, and degenerated or erroneous predictions. In order to solve these problems while preserving favorable model properties, we propose a non-invasive post-hoc orthogonalization (PHO) that guarantees identifiability of model components and provides better estimation and prediction quality. Our theoretical findings are supported by numerical experiments, a benchmark comparison as well as a real-world application to COVID-19 infections.

Related papers

• CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks [5.19656787424626]
  Uncertainty estimation is increasingly attractive for improving the reliability of neural networks. We present novel credal-set interval neural networks (CreINNs) designed for classification tasks.
  arXiv  Detail & Related papers  (2024-01-10T10:04:49Z)
• Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective [67.25782152459851]
  We introduce a novel data-model co-design perspective: to promote superior weight sparsity. Specifically, customized Visual Prompts are mounted to upgrade neural Network sparsification in our proposed VPNs framework.
  arXiv  Detail & Related papers  (2023-12-03T13:50:24Z)
• Generalization and Estimation Error Bounds for Model-based Neural Networks [78.88759757988761]
  We show that the generalization abilities of model-based networks for sparse recovery outperform those of regular ReLU networks. We derive practical design rules that allow to construct model-based networks with guaranteed high generalization.
  arXiv  Detail & Related papers  (2023-04-19T16:39:44Z)
• Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks [59.142826407441106]
  We study the generalization behavior of shallow neural networks (SNNs) by leveraging the concept of algorithmic stability. We consider gradient descent (GD) and gradient descent (SGD) to train SNNs, for both of which we develop consistent excess bounds.
  arXiv  Detail & Related papers  (2022-09-19T18:48:00Z)
• Can pruning improve certified robustness of neural networks? [106.03070538582222]
  We show that neural network pruning can improve empirical robustness of deep neural networks (NNs) Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training. We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
  arXiv  Detail & Related papers  (2022-06-15T05:48:51Z)
• Orthogonal Stochastic Configuration Networks with Adaptive Construction Parameter for Data Analytics [6.940097162264939]
  randomness makes SCNs more likely to generate approximate linear correlative nodes that are redundant and low quality. In light of a fundamental principle in machine learning, that is, a model with fewer parameters holds improved generalization. This paper proposes orthogonal SCN, termed OSCN, to filtrate out the low-quality hidden nodes for network structure reduction.
  arXiv  Detail & Related papers  (2022-05-26T07:07:26Z)
• Robust lEarned Shrinkage-Thresholding (REST): Robust unrolling for sparse recover [87.28082715343896]
  We consider deep neural networks for solving inverse problems that are robust to forward model mis-specifications. We design a new robust deep neural network architecture by applying algorithm unfolding techniques to a robust version of the underlying recovery problem. The proposed REST network is shown to outperform state-of-the-art model-based and data-driven algorithms in both compressive sensing and radar imaging problems.
  arXiv  Detail & Related papers  (2021-10-20T06:15:45Z)
• Ensembles of Spiking Neural Networks [0.3007949058551534]
  This paper demonstrates how to construct ensembles of spiking neural networks producing state-of-the-art results. We achieve classification accuracies of 98.71%, 100.0%, and 99.09%, on the MNIST, NMNIST and DVS Gesture datasets respectively. We formalize spiking neural networks as GLM predictors, identifying a suitable representation for their target domain.
  arXiv  Detail & Related papers  (2020-10-15T17:45:18Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Interpolation between Residual and Non-Residual Networks [24.690238357686134]
  We present a novel ODE model by adding a damping term. It can be shown that the proposed model can recover both a ResNet and a CNN by adjusting an coefficient. Experiments on a number of image classification benchmarks show that the proposed model substantially improves the accuracy of ResNet and ResNeXt.
  arXiv  Detail & Related papers  (2020-06-10T09:36:38Z)
• Error-feedback stochastic modeling strategy for time series forecasting with convolutional neural networks [11.162185201961174]
  We propose a novel Error-feedback Modeling (ESM) strategy to construct a random Convolutional Network (ESM-CNN) Neural time series forecasting task. The proposed ESM-CNN not only outperforms the state-of-art random neural networks, but also exhibits stronger predictive power and less computing overhead in comparison to trained state-of-art deep neural network models.
  arXiv  Detail & Related papers  (2020-02-03T13:30:29Z)

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.