‘Universal joint approximation of manifolds and densities by simple injective flows’, (2021) preprint, M. Puthawala, M. Lassas, I. Dokmanić and M.V. de Hoop View |
‘Convergence rates for learning linear operators from noisy data’, (2021) preprint, N. Kovachki, N. Nelsen, A. Stuart and M.V. de Hoop View |
‘Deep learning architectures for nonlinear operator functions and nonlinear inverse problems’, Mathematical Statistics and Learning (2021) preprint, M.V. de Hoop, M. Lassas and C.A. Wong View |
‘Recurrent scattering network detects metastable behavior in polyphonic seismo-volcanic signals for volcano eruption forecasting’, IEEE Trans. Geosc. and Remote Sensing (2021) in print, doi: 10.1109/TGRS.2021.3134198, A. Bueno, R. Balestriero, S. De Angelis, C. Benítez, L. Zuccarello, R. Baraniuk, J. M. Ibáñez and M.V. de Hoop View |
‘Globally injective ReLU networks’, J. Mach. Learn. Res. (2021) in print, M. Puthawala, K. Kothari, M. Lassas, I. Dokmanić and M.V. de Hoop View |
‘Attention network forecasts time-to-failure in laboratory shear experiments’, J. Geophys. Res. (2021) in print, M.V. de Hoop, H. Jasperson, C. Bolton, P. Johnson, R. Guyer and C. Marone View |
‘Anatomy of continuous Mars SEIS and pressure data from unsupervised learning’, Bulletin of the Seismological Society of America (2021) in print, S. Barkaoui, P. Lognonné, T. Kawamura, E. Stutzmann, L. Seydoux, M.V. de Hoop, R. Balestriero, J.-R. Scholz, G. Sainton, M. Plasman, S. Ceylan, J. Clinton, A. Spiga, R. Widmer-Schnidrig, F. Civilini and W.B. Banerdt. Available via Sponsor Portal |
‘TRUMPETS: Injective flows for inference and inverse problems’, UAI (2021) in print, K. Kothari, A.E. Khorashadizadeh, M.V. de Hoop, and I. Dokmanić View |
‘Learning the geometry of wave-based imaging’, NeurIPS Proceedings: Advances in Neural Processing Systems 33 (2020) K. Kothari, M.V. de Hoop and I. Dokmanić View |
‘Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning’, Nature Comm. 11 (2020) 3972, doi:10.1038/s41467-020-17841- |