Search Results for author:
Found 42 papers, 31 papers with code
Joint Graph Rewiring and Feature Denoising via Spectral Resonance
In graph learning the graph and the node features both contain noisy information about the node labels.
A spring-block theory of feature learning in deep neural networks
A central question in deep learning is how deep neural networks (DNNs) learn features.
Ice-Tide: Implicit Cryo-ET Imaging and Deformation Estimation
We introduce ICE-TIDE, a method for cryogenic electron tomography (cryo-ET) that simultaneously aligns observations and reconstructs a high-resolution volume.
GLIMPSE: Generalized Local Imaging with MLPs
Deep learning is the current de facto state of the art in tomographic imaging.
Implicit Reconstructions from Deformed Projections for CryoET
Cryo-electron tomography (cryoET) is a technique that captures images of biological samples at different tilts, preserving their native state as much as possible.
High-Rate Phase Association with Travel Time Neural Fields
Existing techniques relying on coarsely approximated, fixed wave speed models fail in this unexplored dense regime where the complexity of unknown wave speed cannot be ignored.
A Graph Dynamics Prior for Relational Inference
In this work, we propose a \textit{graph dynamics prior} (GDP) for relational inference.
An Approximation Theory for Metric Space-Valued Functions With A View Towards Deep Learning
Motivated by the developing mathematics of deep learning, we build universal functions approximators of continuous maps between arbitrary Polish metric spaces $\mathcal{X}$ and $\mathcal{Y}$ using elementary functions between Euclidean spaces as building blocks.
Injectivity of ReLU networks: perspectives from statistical physics
Recent work connects this problem to spherical integral geometry giving rise to a conjectured sharp injectivity threshold for $\alpha = \frac{m}{n}$ by studying the expected Euler characteristic of a certain random set.
Deep Injective Prior for Inverse Scattering
Unlike supervised methods that necessitate both scattered fields and target permittivities, our method only requires the target permittivities for training; it can then be used with any experimental setup.
Homophily modulates double descent generalization in graph convolution networks
Motivated by experimental observations of ``transductive'' double descent in key networks and datasets, we use analytical tools from statistical physics and random matrix theory to precisely characterize generalization in simple graph convolution networks on the contextual stochastic block model.
FunkNN: Neural Interpolation for Functional Generation
Our answer is FunkNN -- a new convolutional network which learns how to reconstruct continuous images at arbitrary coordinates and can be applied to any image dataset.
Deep Variational Inverse Scattering
Inverse medium scattering solvers generally reconstruct a single solution without an associated measure of uncertainty.
Differentiable Uncalibrated Imaging
We propose a differentiable imaging framework to address uncertainty in measurement coordinates such as sensor locations and projection angles.
Small Transformers Compute Universal Metric Embeddings
We derive embedding guarantees for feature maps implemented by small neural networks called \emph{probabilistic transformers}.
Manifold Rewiring for Unlabeled Imaging
We illustrate our graph denoising framework on regular synthetic graphs and then apply it to single-particle cryo-EM where the measurements are corrupted by very high levels of noise.
Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown-View Tomography
Unknown-view tomography (UVT) reconstructs a 3D density map from its 2D projections at unknown, random orientations.
Implicit Neural Representation for Mesh-Free Inverse Obstacle Scattering
In this paper, we introduce an implicit neural representation-based framework for solving the inverse obstacle scattering problem in a mesh-free fashion.
Conditional Injective Flows for Bayesian Imaging
Most deep learning models for computational imaging regress a single reconstructed image.
Neural Link Prediction with Walk Pooling
Instead of extracting transition probabilities from the original graph, it computes the transition matrix of a "predictive" latent graph by applying attention to learned features; this may be interpreted as feature-sensitive topology fingerprinting.
Ranked #1 on
Link Prediction
on Pubmed
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows
We show that in general, injective flows between $\mathbb{R}^n$ and $\mathbb{R}^m$ universally approximate measures supported on images of extendable embeddings, which are a subset of standard embeddings: when the embedding dimension m is small, topological obstructions may preclude certain manifolds as admissible targets.
Universal Approximation Under Constraints is Possible with Transformers
Many practical problems need the output of a machine learning model to satisfy a set of constraints, $K$.
Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling
Convolutional neural networks lack shift equivariance due to the presence of downsampling layers.
Trumpets: Injective Flows for Inference and Inverse Problems
We propose injective generative models called Trumpets that generalize invertible normalizing flows.
Localizing Unsynchronized Sensors with Unknown Sources
We look at the general case where neither the emission times of the sources nor the reference time frames of the receivers are known.
Total Least Squares Phase Retrieval
We address the phase retrieval problem with errors in the sensing vectors.
Truly shift-invariant convolutional neural networks
Thanks to the use of convolution and pooling layers, convolutional neural networks were for a long time thought to be shift-invariant.
Learning Multiscale Convolutional Dictionaries for Image Reconstruction
To close the performance gap, we thus propose a multiscale convolutional dictionary structure.
Geometry of Similarity Comparisons
To study this question, we introduce the notions of the \textit{ordinal capacity} of a target space form and \emph{ordinal spread} of the similarity measurements.
Globally Injective ReLU Networks
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 posedness.
Learning the geometry of wave-based imaging
We propose a general physics-based deep learning architecture for wave-based imaging problems.
Hyperbolic Distance Matrices
Hyperbolic space is a natural setting for mining and visualizing data with hierarchical structure.
Fast Optical System Identification by Numerical Interferometry
Our method simplifies the calibration of optical transmission matrices from a quadratic to a linear inverse problem by first recovering the phase of the measurements.
The fastest $\ell_{1,\infty}$ prox in the west
In this paper we study the proximal operator of the mixed $\ell_{1,\infty}$ matrix norm and show that it can be computed in closed form by applying the well-known soft-thresholding operator to each column of the matrix.
Don't take it lightly: Phasing optical random projections with unknown operators
A signal of interest $\mathbf{\xi} \in \mathbb{R}^N$ is mixed by a random scattering medium to compute the projection $\mathbf{y} = \mathbf{A} \mathbf{\xi}$, with $\mathbf{A} \in \mathbb{C}^{M \times N}$ being a realization of a standard complex Gaussian iid random matrix.
Solving Complex Quadratic Systems with Full-Rank Random Matrices
We tackle the problem of recovering a complex signal $\boldsymbol x\in\mathbb{C}^n$ from quadratic measurements of the form $y_i=\boldsymbol x^*\boldsymbol A_i\boldsymbol x$, where $\boldsymbol A_i$ is a full-rank, complex random measurement matrix whose entries are generated from a rotation-invariant sub-Gaussian distribution.
Information Theory Information Theory
Learning Schatten--von Neumann Operators
We study the learnability of a class of compact operators known as Schatten--von Neumann operators.
Geometric Invariants for Sparse Unknown View Tomography
For a point source model, we show that these features reveal geometric information about the model such as the radial and pairwise distances.
Random mesh projectors for inverse problems
We show that in this case the common approach to directly learn the mapping from the measured data to the reconstruction becomes unstable.
Reconstructing Point Sets from Distance Distributions
Our method is the first practical approach to solve the large-scale noisy beltway problem where the points lie on a loop.
Pyroomacoustics: A Python package for audio room simulations and array processing algorithms
We present pyroomacoustics, a software package aimed at the rapid development and testing of audio array processing algorithms.
Sound Audio and Speech Processing
Inverse Problems with Invariant Multiscale Statistics
We propose a new approach to linear ill-posed inverse problems.
Computational Engineering, Finance, and Science
