arXiv research

Paper proves conditions for nonconvex matrix recovery to avoid spurious local minima.

Paper shows moderate RIP is insufficient for avoiding spurious local minima in matrix recovery.

Paper develops TLoc framework to improve Telco outdoor position recovery.

Nonnegative low-rank matrix recovery can have spurious local minima.

Study shows DNNs can recover functions with fewer samples than model parameters at overparameterization.

New method recovers graph latent positions under edge differential privacy.

Paper provides conditions for local recovery of tensor data's Kronecker-structured dictionaries.

We show that there are no spurious local minima in the non-convex factorized parametrization of low-rank matrix recovery from incoherent linear measurements. With noisy measurements we show all local minima are very close to a global optimum. Together with a curvature bound at saddle points, this yields a polynomial ti…

The paper improves conditions for unique recovery in homomorphic sensing of subspaces.

This paper presents the first theoretical results showing that stable identification of overcomplete $μ$-coherent dictionaries $Φ\in \mathbb{R}^{d\times K}$ is locally possible from training signals with sparsity levels $S$ up to the order $O(μ^{-2})$ and signal to noise ratios up to $O(\sqrt{d})$. In particular the di…

The paper analyzes how good initial guesses affect the amount of data needed for low-rank matrix recovery.

The paper analyzes conditions for solving low-rank matrix recovery problems with noisy measurements.

Locally adaptive activation functions boost deep and physics-informed neural networks.

The study examines how side information quality and quantity affect community recovery in graphs.

Exact recovery method for community detection in Gaussian mixtures with dependent noise.

New tensor recovery method uses Riemannian optimization on Segre manifold.

The paper provides recovery guarantees for CNNs with multiple kernels under polynomial sample and computational complexities.

Sharp global guarantees for noisy overparameterized low-rank recovery.

C-kNN-LSH identifies similar patient histories for causal inference in longitudinal data.

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

Paper proposes CLAIR for efficient LLM fine-tuning across clients.

Improved stability for matrix recovery from rank-one measurements.

New algorithm achieves almost exact graph matching in almost quadratic time.

Study on Gaussian-width complexity on statistical manifolds and its applications in learning and recovery.

A new clustering method for non-linear data on manifolds using diffusion distances.

New method improves traffic data recovery for streaming data.

Modified model for Quanto CDS pricing with stochastic recovery and reduced complexity.

Concave regularization methods provide natural procedures for sparse recovery. However, they are difficult to analyze in the high dimensional setting. Only recently a few sparse recovery results have been established for some specific local solutions obtained via specialized numerical procedures. Still, the fundamental…

Optimizing post-crisis recovery in scale-free networks by stimulating high-degree nodes.

StrTransformer recovers sources without labels by optimizing latent matrices and enforcing structural constraints.

Paper finds exact recovery threshold in general hypergraph model.

Study supports recovery of PDEs from noisy data using a specific regularization method.

In this paper, we generalize Huber's criterion to multichannel sparse recovery problem of complex-valued measurements where the objective is to find good recovery of jointly sparse unknown signal vectors from the given multiple measurement vectors which are different linear combinations of the same known elementary vec…

Unified theory explains housing cycle across metros, showing credit expansion impacts.

We consider the problem of recovering a complete (i.e., square and invertible) matrix $\mathbf A_0$, from $\mathbf Y \in \mathbb R^{n \times p}$ with $\mathbf Y = \mathbf A_0 \mathbf X_0$, provided $\mathbf X_0$ is sufficiently sparse. This recovery problem is central to the theoretical understanding of dictionary lear…

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

Study uses Bayes Hilbert framework to recover probability measure flows from sensors.

Study reveals issues with neural autoregressive models and proposes mode recovery cost.

The principal submatrix localization problem deals with recovering a $K\times K$ principal submatrix of elevated mean $μ$ in a large $n\times n$ symmetric matrix subject to additive standard Gaussian noise. This problem serves as a prototypical example for community detection, in which the community corresponds to the …

In the context of sparse recovery, it is known that most of existing regularizers such as $\ell_1$ suffer from some bias incurred by some leading entries (in magnitude) of the associated vector. To neutralize this bias, we propose a class of models with partial regularizers for recovering a sparse solution of a linear …

Local minimax analysis for Poisson deconvolution of discrete signals.

KSS method converges and recovers correct clustering under certain conditions.

We consider the problem of recovering a complete (i.e., square and invertible) matrix $\mathbf A_0$, from $\mathbf Y \in \mathbb{R}^{n \times p}$ with $\mathbf Y = \mathbf A_0 \mathbf X_0$, provided $\mathbf X_0$ is sufficiently sparse. This recovery problem is central to theoretical understanding of dictionary learnin…

Constructing an efficient parameterization of a large, noisy data set of points lying close to a smooth manifold in high dimension remains a fundamental problem. One approach consists in recovering a local parameterization using the local tangent plane. Principal component analysis (PCA) is often the tool of choice, as…

Paper proposes a new method for MRI data recovery using bi-linear modeling.

RTC-GTNLN model recovers traffic data from missing values and noise.

We address the sparse signal recovery problem in the context of multiple measurement vectors (MMV) when elements in each nonzero row of the solution matrix are temporally correlated. Existing algorithms do not consider such temporal correlations and thus their performance degrades significantly with the correlations. I…

Quantization-aware training can recover accuracy lost by post-training quantization.