Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient

• URL: http://arxiv.org/abs/2409.15393v1
• Date: Mon, 23 Sep 2024 03:42:50 GMT
• Title: Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
• Abstract summary: We propose a novel NN named the Approximated Orthogonal Projection Unit (AOPU) which has solid mathematical basis and presents superior training stability. We prove that AOPU attains minimum variance estimation (MVE) in NN, wherein the truncated gradient approximates the natural gradient (NG) Empirical results on two chemical process datasets clearly show that AOPU outperforms other models in achieving stable convergence.
• Score: 3.9858496473361402
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural networks (NN) are extensively studied in cutting-edge soft sensor models due to their feature extraction and function approximation capabilities. Current research into network-based methods primarily focuses on models' offline accuracy. Notably, in industrial soft sensor context, online optimizing stability and interpretability are prioritized, followed by accuracy. This requires a clearer understanding of network's training process. To bridge this gap, we propose a novel NN named the Approximated Orthogonal Projection Unit (AOPU) which has solid mathematical basis and presents superior training stability. AOPU truncates the gradient backpropagation at dual parameters, optimizes the trackable parameters updates, and enhances the robustness of training. We further prove that AOPU attains minimum variance estimation (MVE) in NN, wherein the truncated gradient approximates the natural gradient (NG). Empirical results on two chemical process datasets clearly show that AOPU outperforms other models in achieving stable convergence, marking a significant advancement in soft sensor field.

Related papers

• Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models [7.517070288522858]
  In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint.<n>We show that predicting the data endpoint has a clear training signal that stabilizes training, whereas predicting the velocity maintains stable sampling dynamics near the data manifold.<n>Motivated by these insights, we propose Self-Consistent Flow (SC-Flow), a new method that unifies the benefits of both parameterizations.
  arXiv  Detail & Related papers  (2026-07-13T21:31:45Z)
• Beyond the Ideal: Analyzing the Inexact Muon Update [54.70108543057578]
  We show first analysis of the inexactized update at Muon's core.<n>We reveal a fundamental coupling between this inexactness and the optimal step size and momentum.
  arXiv  Detail & Related papers  (2025-10-22T18:01:07Z)
• NIRVANA: Structured pruning reimagined for large language models compression [50.651730342011014]
  We introduce NIRVANA, a novel pruning method designed to balance immediate zero-shot preservation accuracy with robust fine-tuning.<n>To further address the unique challenges posed by structured pruning, NIRVANA incorporates an adaptive sparsity allocation mechanism across layers and modules.<n>Experiments conducted on Llama3, Qwen, T5 models demonstrate that NIRVANA outperforms existing structured pruning methods under equivalent sparsity constraints.
  arXiv  Detail & Related papers  (2025-09-17T17:59:00Z)
• LaPON: A Lagrange's-mean-value-theorem-inspired operator network for solving PDEs and its application on NSE [8.014720523981385]
  We propose LaPON, an operator network inspired by the Lagrange's mean value theorem.<n>It embeds prior knowledge directly into the neural network architecture instead of the loss function.<n>LaPON provides a scalable and reliable solution for high-fidelity fluid dynamics simulation.
  arXiv  Detail & Related papers  (2025-05-18T10:45:17Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• 10K is Enough: An Ultra-Lightweight Binarized Network for Infrared Small-Target Detection [48.074211420276605]
  Binarized neural networks (BNNs) are distinguished by their exceptional efficiency in model compression.<n>We propose the Binarized Infrared Small-Target Detection Network (BiisNet)<n>BiisNet preserves the core operations of binarized convolutions while integrating full-precision features into the network's information flow.
  arXiv  Detail & Related papers  (2025-03-04T14:25:51Z)
• Which Optimizer Works Best for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks? [1.8175282137722093]
  We compare PINNs and PIKANs on key challenging linear, stiff, multi-scale non-linear PDEs including Burgers, Allen-Cashinsky, Ginzburg-Landau equations. Our results reveal improvements without the use of any other enhancements typically employed in PINNs and PIKANs.
  arXiv  Detail & Related papers  (2025-01-22T21:19:42Z)
• Jacobian-Enforced Neural Networks (JENN) for Improved Data Assimilation Consistency in Dynamical Models [0.0]
  Machine learning-based weather models have shown great promise in producing accurate forecasts but have struggled when applied to data assimilation tasks. This study introduces the Jacobian-Enforced Neural Network (JENN) framework, designed to enhance DA consistency in neural network (NN)-emulated dynamical systems.
  arXiv  Detail & Related papers  (2024-12-02T00:12:51Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  We present Layer-wise Feedback Propagation (LFP), a novel training principle for neural network-like predictors. LFP decomposes a reward to individual neurons based on their respective contributions to solving a given task. Our method then implements a greedy approach reinforcing helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Towards Long-Term predictions of Turbulence using Neural Operators [68.8204255655161]
  It aims to develop reduced-order/surrogate models for turbulent flow simulations using Machine Learning. Different model structures are analyzed, with U-NET structures performing better than the standard FNO in accuracy and stability.
  arXiv  Detail & Related papers  (2023-07-25T14:09:53Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• An Adaptive and Stability-Promoting Layerwise Training Approach for Sparse Deep Neural Network Architecture [0.0]
  This work presents a two-stage adaptive framework for developing deep neural network (DNN) architectures that generalize well for a given training data set. In the first stage, a layerwise training approach is adopted where a new layer is added each time and trained independently by freezing parameters in the previous layers. We introduce a epsilon-delta stability-promoting concept as a desirable property for a learning algorithm and show that employing manifold regularization yields a epsilon-delta stability-promoting algorithm.
  arXiv  Detail & Related papers  (2022-11-13T09:51:16Z)
• 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)
• Physics-aware deep neural networks for surrogate modeling of turbulent natural convection [0.0]
  We investigate the use of PINNs surrogate modeling for turbulent Rayleigh-B'enard convection flows. We show how it comes to play as a regularization close to the training boundaries which are zones of poor accuracy for standard PINNs. The predictive accuracy of the surrogate over the entire half a billion DNS coordinates yields errors for all flow variables ranging between [0.3% -- 4%] in the relative L 2 norm.
  arXiv  Detail & Related papers  (2021-03-05T09:48:57Z)
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search [55.164053971213576]
  convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure. Existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space.
  arXiv  Detail & Related papers  (2020-11-04T07:43:01Z)
• A Novel Neural Network Training Framework with Data Assimilation [2.948167339160823]
  A gradient-free training framework based on data assimilation is proposed to avoid the calculation of gradients. The results show that the proposed training framework performed better than the gradient decent method.
  arXiv  Detail & Related papers  (2020-10-06T11:12:23Z)
• 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)
• Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks [78.76880041670904]
  In neural networks with binary activations and or binary weights the training by gradient descent is complicated. We propose a new method for this estimation problem combining sampling and analytic approximation steps. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models.
  arXiv  Detail & Related papers  (2020-06-04T21:51:21Z)

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.