paper-with-me

홈 › Papers

OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case

2025-09-09 · Ratna Khatri, Anthony Kolshorn, Colin Olson, Harbir Antil arxiv

This paper presents a novel, mathematically rigorous framework for autoencoder-type deep neural networks that combines optimal control theory and low-rank tensor methods to yield memory-efficient training and automated architecture discovery. The learning task is formulated as an optimization problem constrained by differential equations representing the encoder and decoder components of the network and the corresponding optimality conditions are derived via a Lagrangian approach. Efficient memory compression is enabled by approximating differential equation solutions on low-rank tensor manifolds using an adaptive explicit integration scheme. These concepts are combined to form OCTANE (Optimal Control for Tensor-based Autoencoder Network Emergence) -- a unified training framework that yields compact autoencoder architectures, reduces memory usage, and enables effective learning, even with limited training data. The framework's utility is illustrated with application to image denoising and deblurring tasks and recommendations regarding governing hyperparameters are provided.

📄 PDF Abstract BibTeX arXiv:2509.08169

Code (0)

등록된 구현이 없습니다.

Tasks

Image Denoising

Similar Papers 제목 키워드 기반

Graph Machine Learning for Design of High-Octane Fuels

2022-06-01 · Jan G. Rittig, Martin Ritzert, Artur M. Schweidtmann, Stefanie Winkler 외

Fuels with high-knock resistance enable modern spark-ignition engines to achieve high efficiency and thus low CO2 emissions. Identification of molecules with desired autoignition properties indicated by a high research o…

Bayesian OptimizationBIG-bench Machine LearningVocal Bursts Intensity Prediction

Mode-Aware Non-Linear Tucker Autoencoder for Tensor-based Unsupervised Learning

2025-08-09 · Junjing Zheng, Chengliang Song, Weidong Jiang, Xinyu Zhang arxiv

High-dimensional data, particularly in the form of high-order tensors, presents a major challenge in self-supervised learning. While MLP-based autoencoders (AE) are commonly employed, their dependence on flattening opera…

Self-Supervised Learning

Control theoretically explainable application of autoencoder methods to fault detection in nonlinear dynamic systems

2022-08-02 · Linlin Li, Steven X. Ding, Ketian Liang, Zhiwen Chen 외

This paper is dedicated to control theoretically explainable application of autoencoders to optimal fault detection in nonlinear dynamic systems. Autoencoder-based learning is a standard machine learning method and widel…

Anomaly DetectionFault DetectionRepresentation Learning

Nonlinear State Space Modeling and Control of the Impact of Patients' Modifiable Lifestyle Behaviors on the Emergence of Multiple Chronic Conditions

2021-07-14 · Syed Hasib Akhter Faruqui, Adel Alaeddini, Jing Wang, Susan P Fisher-Hoch 외

The emergence and progression of multiple chronic conditions (MCC) over time often form a dynamic network that depends on patient's modifiable risk factors and their interaction with non-modifiable risk factors and exist…

tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder

2020-06-08 · Alex Campbell, Pietro Liò

Variational autoencoders (VAEs) are a powerful class of deep generative latent variable model for unsupervised representation learning on high-dimensional data. To ensure computational tractability, VAEs are often implem…

Gaussian ProcessesRepresentation LearningTime SeriesTime Series Analysis