59 citations · 73 across the 7 of their papers we have counts for
6 papers · 1 filter
Motion Equivariant Convolutional LSTM: When Motion Becomes a Gauge Symmetry
Vahid Hosseinzadeh, T. Anderson Keller, Michael Puthawala
Objects move, cameras pan, and weather drifts with the wind: much of what changes in sequential data is motion. Motion changes where things are, not what they are, and is therefore…
Can neural operators always be continuously discretized?
Takashi Furuya, Michael Puthawala, Maarten V. de Hoop +1
We consider the problem of discretization of neural operators between Hilbert spaces in a general framework including skip connections. We focus on bijective neural operators throu…
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…
Deep Invertible Approximation of Topologically Rich Maps between Manifolds
Michael Puthawala, Matti Lassas, Ivan Dokmanic +2
How can we design neural networks that allow for stable universal approximation of maps between topologically interesting manifolds? The answer is with a coordinate projection. Neu…
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…