arXiv research

GRRT recovers sparse signals without prior sparsity or noise variance knowledge.

Survey on robust data representation learning from a knowledge flow perspective.

Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.

Recovering manifold geometry from geodesic intersections.

Recovering the support of sparse vectors in underdetermined linear regression models, \textit{aka}, compressive sensing is important in many signal processing applications. High SNR consistency (HSC), i.e., the ability of a support recovery technique to correctly identify the support with increasing signal to noise rat…

This work provides a guaranteed tensor recovery method by combining low-rankness and smoothness priors.

We have observed an interesting, yet unexplained, phenomenon: Semidefinite programming (SDP) based relaxations of maximum likelihood estimators (MLE) tend to be tight in recovery problems with noisy data, even when MLE cannot exactly recover the ground truth. Several results establish tightness of SDP based relaxations…

Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and app…

Deep RL trains a robust humanoid push-recovery policy.

Paper develops TLoc framework to improve Telco outdoor position recovery.

Sharp threshold for exact recovery in non-uniform hypergraph stochastic block model.

We examine the recovery of block sparse signals and extend the framework in two important directions; one by exploiting signals' intra-block correlation and the other by generalizing signals' block structure. We propose two families of algorithms based on the framework of block sparse Bayesian learning (BSBL). One fami…

Paper calculates loan loss after default using Bayesian model.

Paper improves compressed sensing with prior probability information.

Study robust recovery of low-rank matrices from corrupted measurements without rank prior.

Efficient algorithm for robust recovery in stochastic block models.

Proposes using equivariant generative models for compressed sensing with unknown orientations.

This paper advances FL algorithms for composite optimization and statistical recovery.

We consider the exact recovery problem in the hypergraph stochastic block model (HSBM) with $k$ blocks of equal size. More precisely, we consider a random $d$-uniform hypergraph $H$ with $n$ vertices partitioned into $k$ clusters of size $s = n / k$. Hyperedges $e$ are added independently with probability $p$ if $e$ is…

Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of $\ell_1$ regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped …

Sparse matrices are favorable objects in machine learning and optimization. When such matrices are used, in place of dense ones, the overall complexity requirements in optimization can be significantly reduced in practice, both in terms of space and run-time. Prompted by this observation, we study a convex optimization…

Theoretical justification for image inpainting using diffusion models.

Orthogonal matching pursuit (OMP) is a widely used algorithm for recovering sparse high dimensional vectors in linear regression models. The optimal performance of OMP requires \textit{a priori} knowledge of either the sparsity of regression vector or noise statistics. Both these statistics are rarely known \textit{a p…

Paper explores limits of high-order clustering with planted structures.

New model for multivariate discrete event data with flexible interactions.

The paper sets information-theoretic lower bounds for neural networks' parameter recovery and excess risk.

New findings on computational limits for estimating hidden structures.

Method recovers particle orientations from cryo-EM projections.

Inferring the functional specificity of brain regions from functional Magnetic Resonance Images (fMRI) data is a challenging statistical problem. While the General Linear Model (GLM) remains the standard approach for brain mapping, supervised learning techniques (a.k.a.} decoding) have proven to be useful to capture mu…

New method for community detection in sparse directed SBMs with exact recovery guarantees.

b-LOAD extends local causal discovery with prior knowledge, improving causal effect estimation.

The non-negative solution to an underdetermined linear system can be uniquely recovered sometimes, even without imposing any additional sparsity constraints. In this paper, we derive conditions under which a unique non-negative solution for such a system can exist, based on the theory of polytopes. Furthermore, we deve…

In this paper, we develop a relative error bound for nuclear norm regularized matrix completion, with the focus on the completion of full-rank matrices. Under the assumption that the top eigenspaces of the target matrix are incoherent, we derive a relative upper bound for recovering the best low-rank approximation of t…

In this paper we show that in anisotropic elasticity, in the particular case of transversely isotropic media, under appropriate convexity conditions, knowledge of the qSH wave travel times determines the tilt of the axis of isotropy as well as some of the elastic material parameters, and the knowledge of qP and qSV tra…

We propose a flexible method for estimating value functions in reinforcement learning without parametric assumptions.

Binary Iterative Hard Thresholding converges with optimal number of 1-bit measurements.

Chemical plants are complex and dynamical systems consisting of many components for manipulation and sensing, whose state transitions depend on various factors such as time, disturbance, and operation procedures. For the purpose of supporting human operators of chemical plants, we are developing an AI system that can s…

DeepFPC uses neural networks to recover sparse signals from quantized measurements.

New spectral clustering method handles discrete covariates for better community detection.

Linear problems appear in a variety of disciplines and their application for the transmission matrix recovery is one of the most stimulating challenges in biomedical imaging. Its knowledge turns any random media into an optical tool that can focus or transmit an image through disorder. Here, converting an input-output …

EBM predicts protein conformations at atomic scale using crystallized data.

Standard compressive sensing results state that to exactly recover an s sparse signal in R^p, one requires O(s. log(p)) measurements. While this bound is extremely useful in practice, often real world signals are not only sparse, but also exhibit structure in the sparsity pattern. We focus on group-structured patterns …

We study the problem of demixing a pair of sparse signals from noisy, nonlinear observations of their superposition. Mathematically, we consider a nonlinear signal observation model, $y_i = g(a_i^Tx) + e_i, \ i=1,\ldots,m$, where $x = Φw+Ψz$ denotes the superposition signal, $Φ$ and $Ψ$ are orthonormal bases in $\mathb…

PREMA recovers detailed data from aggregated views.

This work improves dictionary learning speed without sacrificing accuracy.

In this paper, we consider parameter recovery for non-overlapping convolutional neural networks (CNNs) with multiple kernels. We show that when the inputs follow Gaussian distribution and the sample size is sufficiently large, the squared loss of such CNNs is $\mathit{~locally~strongly~convex}$ in a basin of attraction…

Plug-and-play L-GM-AMP improves CS recovery for any i.i.d. source prior.

Orthogonal matching pursuit (OMP) and orthogonal least squares (OLS) are widely used for sparse signal reconstruction in under-determined linear regression problems. The performance of these compressed sensing (CS) algorithms depends crucially on the \textit{a priori} knowledge of either the sparsity of the signal ($k_…