2 citations · 6 across the 15 of their papers we have counts for
15 papers
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…
On Observation Time for Recovering Latent Hawkes Networks
Jonas Linkerhägner, Michele Bortolasi, Lorenzo Baldassari +2
Dynamics of interacting systems in engineering, society, and nature often evolve over latent networks that govern which entities can interact. We study the problem of inferring the…
Joint Graph Rewiring and Feature Denoising via Spectral Resonance
Jonas Linkerhägner, Cheng Shi, Ivan Dokmanić
When learning from graph data, the graph and the node features both give noisy information about the node labels. In this paper we propose an algorithm to jointly denoise the featu…
Spring-block theory of feature learning in deep neural networks
Cheng Shi, Liming Pan, Ivan Dokmanić
Feature-learning deep nets progressively collapse data to a regular low-dimensional geometry. How this emerges from the collective action of nonlinearity, noise, learning rate, and…
Ice-Tide: Implicit Cryo-ET Imaging and Deformation Estimation
Valentin Debarnot, Vinith Kishore, Ricardo D. Righetto +1
We introduce ICE-TIDE, a method for cryogenic electron tomography (cryo-ET) that simultaneously aligns observations and reconstructs a high-resolution volume. The alignment of tilt…
Glimpse: Generalized Locality for Scalable and Robust CT
AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu +1
Deep learning has become the state-of-the-art approach to medical tomographic imaging. A common approach is to feed the result of a simple inversion, for example the backprojection…
A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression
Tin Sum Cheng, Aurelien Lucchi, Ivan Dokmanić +2
Existing statistical learning guarantees for general kernel regressors often yield loose bounds when used with finite-rank kernels. Yet, finite-rank kernels naturally appear in sev…
Implicit Reconstructions from Deformed Projections for CryoET
Vinith Kishore, Valentin Debarnot, Ivan Dokmanić
Cryo-electron tomography (cryoET) is a technique that captures images of biological samples at different tilts, preserving their native state as much as possible. Along with the pa…
High-Rate Phase Association with Travel Time Neural Fields
Cheng Shi, Giulio Poggiali, Chris Marone +2
Earthquake science and seismology rely on the ability to associate seismic waves with their originating earthquakes. Earthquake detection algorithms based on deep learning have pro…
A Graph Dynamics Prior for Relational Inference
Liming Pan, Cheng Shi, Ivan Dokmanić
Relational inference aims to identify interactions between parts of a dynamical system from the observed dynamics. Current state-of-the-art methods fit the dynamics with a graph ne…
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…
Injectivity of ReLU networks: perspectives from statistical physics
Antoine Maillard, Afonso S. Bandeira, David Belius +2
When can the input of a ReLU neural network be inferred from its output? In other words, when is the network injective? We consider a single layer, , w…
Deep Injective Prior for Inverse Scattering
AmirEhsan Khorashadizadeh, Vahid Khorashadizadeh, Sepehr Eskandari +2
In electromagnetic inverse scattering, the goal is to reconstruct object permittivity using scattered waves. While deep learning has shown promise as an alternative to iterative so…
FunkNN: Neural Interpolation for Functional Generation
AmirEhsan Khorashadizadeh, Anadi Chaman, Valentin Debarnot +1
Can we build continuous generative models which generalize across scales, can be evaluated at any coordinate, admit calculation of exact derivatives, and are conceptually simple? E…
Homophily modulates double descent generalization in graph convolution networks
Cheng Shi, Liming Pan, Hong Hu +1
Graph neural networks (GNNs) excel in modeling relational data such as biological, social, and transportation networks, but the underpinnings of their success are not well understo…