Signals, Waves, and Learning: A Data-Driven Paradigm for Wave-Based Inverse Problems

Información del proyecto

SWING

Identificador del acuerdo de subvención: 852821

DOI

10.3030/852821

Proyecto cerrado

Fecha de la firma de la CE 30 Octubre 2019

Fecha de inicio 1 Enero 2020

Fecha de finalización 31 Diciembre 2024

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 986 430,00

Aportación de la UE

€ 1 986 430,00

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Other (8)

Neural equilibria for long-term prediction of nonlinear conservation laws

Autores: J. Antonio Lara Benitez, Junyi Guo, Kareem Hegazy, Ivan Dokmanić, Michael W. Mahoney, Maarten V. de Hoop
Publicado en: 2025
Editor: arXiv
DOI: 10.48550/arxiv.2501.06933

Conditional Injective Flows for Bayesian Imaging

Autores: AmirEhsan Khorashadizadeh, Konik Kothari, Leonardo Salsi, Ali Aghababaei Harandi, Maarten de Hoop, Ivan Dokmanić
Publicado en: 2022
Editor: NA

A spring-block theory of feature learning in deep neural networks

Autores: Cheng Shi, Liming Pan, Ivan Dokmanić
Publicado en: 2024
Editor: arXiv

An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning

Autores: Kratsios, Anastasis; Liu, Chong; Lassas, Matti; de Hoop, Maarten V.; Dokmanić, Ivan
Publicado en: Edición 4, 2023
Editor: arXiv
DOI: 10.48550/arxiv.2304.12231

LoFi: Neural Local Fields for Scalable Image Reconstruction

Autores: AmirEhsan Khorashadizadeh, Tobías I. Liaudat, Tianlin Liu, Jason D. McEwen, Ivan Dokmanić
Publicado en: 2024
Editor: arXiv

End-to-end localized deep learning for Cryo-ET

Autores: Vinith Kishore, Valentin Debarnot, Ricardo D. Righetto, AmirEhsan Khorashadizadeh, Ivan Dokmanić
Publicado en: 2025
Editor: arXiv
DOI: 10.48550/arxiv.2501.15246

Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown-View Tomography

Autores: Shuai Huang, Mona Zehni, Ivan Dokmanic, Zhizhen Zhao
Publicado en: arXiv, 2022
Editor: NA

High-Rate Phase Association with Travel Time Neural Fields

Autores: Cheng Shi, Giulio Poggiali, Chris Marone, Maarten V. de Hoop, Ivan Dokmanić
Publicado en: 2024
Editor: arXiv
DOI: 10.48550/arxiv.2307.07572

Peer reviewed articles (16)

Total Least Squares Phase Retrieval

Autores: Sidharth Gupta, Ivan Dokmanic
Publicado en: IEEE Transactions on Signal Processing, Edición 70, 2024, Página(s) 536-549, ISSN 1053-587X
Editor: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tsp.2021.3128750

Ice-Tide: Implicit Cryo-ET Imaging and Deformation Estimation

Autores: Valentin Debarnot, Vinith Kishore, Ricardo D. Righetto, Ivan Dokmanić
Publicado en: IEEE Transactions on Computational Imaging, Edición 11, 2025, Página(s) 24-35, ISSN 2333-9403
Editor: IEEE
DOI: 10.1109/tci.2024.3519805

Differentiable Uncalibrated Imaging

Autores: Sidharth Gupta, Konik Kothari, Valentin Debarnot, Ivan Dokmanić
Publicado en: IEEE Transactions on Computational Imaging, Edición 10, 2024, Página(s) 1-16, ISSN 2333-9403
Editor: IEEE
DOI: 10.1109/tci.2023.3346294

Deep Injective Prior for Inverse Scattering

Autores: AmirEhsan Khorashadizadeh, Vahid Khorashadizadeh, Sepehr Eskandari, Guy A. E. Vandenbosch, Ivan Dokmanić
Publicado en: IEEE Transactions on Antennas and Propagation, Edición 71, 2023, Página(s) 8894-8906, ISSN 0018-926X
Editor: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tap.2023.3312818

Conditional Injective Flows for Bayesian Imaging

Autores: AmirEhsan Khorashadizadeh, Konik Kothari, Leonardo Salsi, Ali Aghababaei Harandi, Maarten de Hoop, Ivan Dokmanić
Publicado en: IEEE Transactions on Computational Imaging, Edición 9, 2024, Página(s) 224-237, ISSN 2333-9403
Editor: IEEE
DOI: 10.1109/tci.2023.3248949

Injectivity of ReLU networks: Perspectives from statistical physics

Autores: Antoine Maillard, Afonso S. Bandeira, David Belius, Ivan Dokmanić, Shuta Nakajima
Publicado en: Applied and Computational Harmonic Analysis, Edición 76, 2025, Página(s) 101736, ISSN 1063-5203
Editor: Academic Press
DOI: 10.1016/j.acha.2024.101736

Learning Multiscale Convolutional Dictionaries for Image Reconstruction

Autores: Tianlin Liu, Anadi Chaman, David Belius, Ivan Dokmanić
Publicado en: IEEE Transactions on Computational Imaging, 2022, ISSN 2333-9403
Editor: IEEE

WaveBench: Benchmarking Data-driven Solvers for Linear Wave Propagation PDEs

Autores: Liu, Tianlin; Lara Benitez, Jose Antonio; Faucher, Florian; Khorashadizadeh, Amirehsan; de Hoop, Maarten; Dokmanić, Ivan
Publicado en: Transactions on Machine Learning Research Journal, Edición 1, 2024, ISSN 2835-8856
Editor: OpenReview.net

Homophily modulates double descent generalization in graph convolution networks

Autores: Cheng Shi, Liming Pan, Hong Hu, Ivan Dokmanić
Publicado en: Proceedings of the National Academy of Sciences, Edición 121, 2024, ISSN 0027-8424
Editor: National Academy of Sciences
DOI: 10.1073/pnas.2309504121

Learning sub-patterns in piecewise continuous functions

Autores: Kratsios, Anastasis; Zamanlooy, Behnoosh
Publicado en: Neurocomputing, Edición 09252312, 2022, ISSN 0925-2312
Editor: Elsevier BV
DOI: 10.1016/j.neucom.2022.01.036

Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown View Tomography

Autores: Shuai Huang, Mona Zehni, Ivan Dokmanić, Zhizhen Zhao
Publicado en: SIAM Journal on Imaging Sciences, Edición 16, 2024, Página(s) 1398-1439, ISSN 1936-4954
Editor: Society for Industrial and Applied Mathematics
DOI: 10.1137/22m1498218

Globally Injective ReLU Networks

Autores: Michael Puthawala, Konik Kothari, Matti Lassas, Ivan Dokmanić, Maarten de Hoop
Publicado en: Journal of Machine Learning Research, 2022, ISSN 1532-4435
Editor: MIT Press

Learning Multiscale Convolutional Dictionaries for Image Reconstruction

Autores: Tianlin Liu, Anadi Chaman, David Belius, Ivan Dokmanic
Publicado en: IEEE Transactions on Computational Imaging, Edición 8, 2022, Página(s) 425-437, ISSN 2333-9403
Editor: IEEE
DOI: 10.1109/tci.2022.3175309

Total Least Squares Phase Retrieval

Autores: Sidharth Gupta, Ivan Dokmanić
Publicado en: IEEE Transactions on Signal Processing, 2021, ISSN 1941-0476
Editor: IEEE

A Graph Dynamics Prior for Relational Inference

Autores: Liming Pan, Cheng Shi, Ivan Dokmanic
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 38, 2024, Página(s) 14508-14516, ISSN 2374-3468
Editor: AAAI Press
DOI: 10.1609/aaai.v38i13.29366

Designing universal causal deep learning models: The geometric (Hyper)transformer

Autores: Beatrice Acciaio, Anastasis Kratsios, Gudmund Pammer
Publicado en: Mathematical Finance, Edición 34, 2024, Página(s) 671-735, ISSN 0960-1627
Editor: Blackwell Publishing Inc.
DOI: 10.1111/mafi.12389

Conference proceedings (14)

Truly shift-invariant convolutional neural networks

Autores: Anadi Chaman, Ivan Dokmanic
Publicado en: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, Página(s) 3772-3782
Editor: IEEE
DOI: 10.1109/cvpr46437.2021.00377

Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows

Autores: Michael Puthawala, Matti Lassas, Ivan Dokmanic, Maarten De Hoop
Publicado en: Proceedings of the 39th International Conference on Machine Learning, 2022
Editor: PMLR

Joint Graph Rewiring and Feature Denoising via Spectral Resonance

Autores: Jonas Linkerhägner, Cheng Shi, Ivan Dokmanić
Publicado en: The Thirteenth International Conference on Learning Representations (ICLR), 2025
Editor: OpenReview.net
DOI: 10.48550/arxiv.2408.07191

Deep Variational Inverse Scattering : (Invited Paper)

Autores: AmirEhsan Khorashadizadeh, Ali Aghababaei, Tin Vlašić, Hieu Nguyen, Ivan Dokmanić
Publicado en: 2023 17th European Conference on Antennas and Propagation (EuCAP), 2024, Página(s) 1-5
Editor: IEEE
DOI: 10.23919/eucap57121.2023.10133365

Neural Link Prediction with Walk Pooling

Autores: Liming Pan, Cheng Shi, Ivan Dokmanic
Publicado en: International Conference on Learning Representations, 2022
Editor: Tenth International Conference on Learning Representations

Universal Approximation Under Constraints is Possible with Transformers

Autores: Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu, Ivan Dokmanic
Publicado en: International Conference on Learning Representations, 2022
Editor: ICLR

Truly Shift-Invariant Convolutional Neural Networks

Autores: Anadi Chaman, Ivan Dokmanic
Publicado en: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Editor: IEEE

Trumpets: Injective Flows for Inference and Inverse Problems

Autores: Kothari, Konik; Khorashadizadeh, AmirEhsan; de Hoop, Maarten; Dokmanić, Ivan
Publicado en: Conference on Uncertainty in Artificial Intelligence (UAI), 2021
Editor: NA

Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering

Autores: Tin Vlašić, Hieu Nguyen, Ivan Dokmanić
Publicado en: Asilomar Conference on Signals, Systems, and Computers, 2022
Editor: NA

Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling

Autores: Anadi Chaman, Ivan Dokmanić
Publicado en: 2021 55th Asilomar Conference on Signals, Systems, and Computers, 2021
Editor: IEEE

Manifold Rewiring for Unlabeled Imaging

Autores: Valentin Debarnot, Vinith Kishore, Cheng Shi, Ivan Dokmanic
Publicado en: APSIPA, 2022
Editor: IEEE

Joint Cryo-ET Alignment and Reconstruction with Neural Deformation Fields

Autores: Valentin Debarnot, Sidharth Gupta, Konik Kothari, Ivan Dokmanić
Publicado en: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, Página(s) 1-5
Editor: IEEE
DOI: 10.1109/icassp49357.2023.10095454

Learning the Geometry of Wave-Based Imaging

Autores: Konik Kothari, Maarten de Hoop, Ivan Dokmanić
Publicado en: Advances in Neural Information Processing Systems, Edición 33, 2020
Editor: Advances in Neural Information Processing Systems

SeisLM: a Foundation Model for Seismic Waveforms

Autores: Tianlin Liu, Jannes Münchmeyer, Laura Laurenti, Chris Marone, Maarten V. de Hoop, Ivan Dokmanić
Publicado en: NeurIPS 2024 workshop on Foundation Models for Science: Progress, Opportunities, and Challenges, 2024
Editor: NA