Search

Your search keyword '"Sparse Variational Gaussian Processes"' showing total 4 results
Start Over Descriptor "Sparse Variational Gaussian Processes"
4 results on '"Sparse Variational Gaussian Processes"'

1. End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes

Author

Bellet, Valentine, Fauvel, Mathieu, Inglada, Jordi, Michel, Julien, Centre d'études spatiales de la biosphère (CESBIO), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Université de Toulouse (UT), and ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019)

Subjects
[SHS.STAT]Humanities and Social Sciences/Methods and statistics, Satellite Image Time Series SITS, [SDE.IE]Environmental Sciences/Environmental Engineering, Land Cover Map, Sparse Variational Gaussian Processes, Classification, Earth Observation (EO), Irregular Sampling, Large Scale, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Remote Sensing, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Sentinel-2, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Published
2023

2. Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features

Author

Valentine Bellet, Mathieu Fauvel, Jordi Inglada, Centre d'études spatiales de la biosphère (CESBIO), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Centre National d'Études Spatiales [Toulouse] (CNES), Centre National d’Etudes Spatiales (CNES), ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019), Bellet, Valentine, Artificial and Natural Intelligence Toulouse Institute - - ANITI2019 - ANR-19-P3IA-0004 - P3IA - VALID, Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Satellite Image Time-Series (SITS), Land Cover Map, Land Cover Pixel-Based Classification, Sparse Variational Gaussian Processes, [MATH] Mathematics [math], Classification, Earth Observation (EO), [SDU.ENVI] Sciences of the Universe [physics]/Continental interfaces, environment, Large Scale, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Remote Sensing, Pixel-Based, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], General Earth and Planetary Sciences, Sentinel- 2, Electrical and Electronic Engineering, [MATH]Mathematics [math], [SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces, environment, [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST]
Abstract

In this article, we propose an approach based on Gaussian Processes (GP) for large scale land cover pixel-basedclassification with Sentinel-2 satellite image time-series (SITS). We used a sparse approximation of the posterior combined with variational inference to learn the GP’s parameters. We applied stochastic gradient descent and GPU computing to optimize our GP models on massive data sets. The proposed GP model can be trained with hundreds of thousands of samples, compared to few thousands for traditional GP methods. Moreover, we included the spatial information by adding the geographic coordinates into the GP’s covariance function to efficiently exploit the spatio-spectro-temporal structure of the SITS. We ran experiments with Sentinel-2 SITS of the full year 2018 over an area of 200 000 km 2 (about 2 billion pixels) in the south of France, which is representative of an operational setting. Adding the spatial information significantly improved the results in terms of classification accuracy. With spatial information, GP models have an overall accuracy of 79.8. They are more than three points above Random Forest (the method used for current operational systems) and more than one point above a multi-layer perceptron. Compared to a Transformer-based model (which provides state ofthe art results in the literature, but are not applied in operational systems), GP models are only one point below.

Published
2023
Full Text
View/download PDF

3. Physics-model-free heat-electricity energy management of multiple microgrids based on surrogate model-enabled multi-agent deep reinforcement learning.

Author

Li, Sichen, Hu, Weihao, Cao, Di, Chen, Zhe, Huang, Qi, Blaabjerg, Frede, and Liao, Kaiji

Subjects
*REINFORCEMENT learning, *DEEP learning, *ENERGY management, *MICROGRIDS, *POWER resources, *ELECTRICAL load, *ASTRONAUTICS
Abstract

• The proposed control framework mitigates assumptions about accurate physical models. • A novel exploration mechanism incorporates historical information representation. • Each MG controller can manage the energy of MG in a decentralized manner. Reliability and cost-effectiveness in the operation of the multiple microgrid (MMG) system depend on the skillful management of its energy resources. Traditional energy management approaches are physics-model-based, which rely on the precise system parameters (e.g., line parameters) of the electricity and heat network. It is difficult to establish the precise system parameters in practice because they depend on a variety of factors. In this context, this paper proposes a physics-model-free control framework for the energy management of MMGs with heat-electricity energy, consisting of proposed surrogate model and multi-agent deep reinforcement learning (MADRL) approach. An important step is to use historical data to train a surrogate model in supervised manner that can imitate the realistic power and thermal flow calculations. Meanwhile, the energy management problem is reformulated as a Markov game. It is solved by the proposed MADRL-based approach by modeling each MG controller as an agent with a specific objective. The historical trajectories representation, parameter space technology, and deep dense architecture in reinforcement learning are introduced in MADRL to overcome the negative impact brought by the time series data from the input state on the decision-making process and construct an efficient exploration mechanism to overcome inefficient optimization of the MMG system in a multi-agent setting. During training period of MADRL, the trained surrogate models integrate into the environment of the MADRL, which can develop optimal energy management strategy based on the continuous interaction with the surrogate models. The proposed surrogate model enabled MADRL approach can reduce the reliance on precise physical systems and prevent having an impact on the real system while being trained involving trial and error process. Simulation results demonstrate the effectiveness of the proposed control framework. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

4. Connections and Equivalences between the Nystr\'om Method and Sparse Variational Gaussian Processes

Author

Wild, Veit, Kanagawa, Motonobu, Sejdinovic, Dino, Department of Statistics [Oxford], University of Oxford [Oxford], Eurecom [Sophia Antipolis], ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019), Eurecom, Centre De Documentation, and 3IA Côte d'Azur - - 3IA@cote d'azur2019 - ANR-19-P3IA-0002 - P3IA - VALID

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Nyström Method, Sparse Variational Gaussian Processes, Machine Learning (stat.ML), Mathematics - Statistics Theory, Statistics Theory (math.ST), [INFO.INFO-IA]Computer Science [cs]/Computer Aided Engineering, [INFO.INFO-IA] Computer Science [cs]/Computer Aided Engineering, Machine Learning (cs.LG), Methodology (stat.ME), Sparse Approximation, Kernel Methods, Statistics - Machine Learning, FOS: Mathematics, Gaussian Processes, Statistics - Methodology
Abstract

We investigate the connections between sparse approximation methods for making kernel methods and Gaussian processes (GPs) scalable to large-scale data, focusing on the Nystr\"om method and the Sparse Variational Gaussian Processes (SVGP). While sparse approximation methods for GPs and kernel methods share some algebraic similarities, the literature lacks a deep understanding of how and why they are related. This may pose an obstacle to the communications between the GP and kernel communities, making it difficult to transfer results from one side to the other. Our motivation is to remove this obstacle, by clarifying the connections between the sparse approximations for GPs and kernel methods. In this work, we study the two popular approaches, the Nystr\"om and SVGP approximations, in the context of a regression problem, and establish various connections and equivalences between them. In particular, we provide an RKHS interpretation of the SVGP approximation, and show that the Evidence Lower Bound of the SVGP contains the objective function of the Nystr\"om approximation, revealing the origin of the algebraic equivalence between the two approaches. We also study recently established convergence results for the SVGP and how they are related to the approximation quality of the Nystr\"om method., Comment: 39 pages

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results