90 citations · 503 across the 77 of their papers we have counts for
9 papers · 1 filter
Function graph transformers universally approximate operators between function spaces
Takashi Furuya, David Mis, Ivan Dokmanić +2
We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on their graphs and leverage a re…
Flowers: A Warp Drive for Neural PDE Solvers
Till Muser, Alexandra Spitzer, Matti Lassas +2
We introduce Flowers, a neural architecture for learning PDE solution operators built entirely from multihead warps. Aside from pointwise channel mixing and a multiscale scaffold,…
Globally injective and bijective neural operators
Takashi Furuya, Michael Puthawala, Matti Lassas +1
Recently there has been great interest in operator learning, where networks learn operators between function spaces from an essentially infinite-dimensional perspective. In this wo…
Multi-scale clustering and source separation of InSight mission seismic data
Ali Siahkoohi, Rudy Morel, Randall Balestriero +4
Unsupervised source separation involves unraveling an unknown set of source signals recorded through a mixing operator, with limited prior knowledge about the sources, and only acc…
An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning
Anastasis Kratsios, Chong Liu, Matti Lassas +2
Motivated by the developing mathematics of deep learning, we build universal functions approximators of continuous maps between arbitrary Polish metric spaces and $\m…
Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data
Ali Siahkoohi, Rudy Morel, Maarten V. de Hoop +3
Source separation involves the ill-posed problem of retrieving a set of source signals that have been observed through a mixing operator. Solving this problem requires prior knowle…
Beyond Hawkes: Neural Multi-event Forecasting on Spatio-temporal Point Processes
Negar Erfanian, Santiago Segarra, Maarten de Hoop
Predicting discrete events in time and space has many scientific applications, such as predicting hazardous earthquakes and outbreaks of infectious diseases. History-dependent spat…
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
Michael Puthawala, Matti Lassas, Ivan Dokmanić +1
We study approximation of probability measures supported on -dimensional manifolds embedded in by injective flows -- neural networks composed of invertible flows…
Globally Injective ReLU Networks
Michael Puthawala, Konik Kothari, Matti Lassas +2
Injectivity plays an important role in generative models where it enables inference; in inverse problems and compressed sensing with generative priors it is a precursor to well pos…