arXiv research

Sign-RIP improves robust low-rank matrix recovery by preserving norms even with corrupted measurements.

We propose a general modeling and algorithmic framework for discrete structure recovery that can be applied to a wide range of problems. Under this framework, we are able to study the recovery of clustering labels, ranks of players, signs of regression coefficients, cyclic shifts, and even group elements from a unified…

Paper offers robust recovery for 1-bit sensing with partial Gaussian circulant matrices.

Sign information is the key to overcoming the inevitable saturation error in compressive sensing systems, which causes information loss and results in bias. For sparse signal recovery from saturation, we propose to use a linear loss to improve the effectiveness from existing methods that utilize hard constraints/hinge …

Study on signed graphs with random signs, focusing on community detection.

Efficiently recovers network community structure from clients' small subgraphs.

Consider the recovery of an unknown signal ${x}$ from quantized linear measurements. In the one-bit compressive sensing setting, one typically assumes that ${x}$ is sparse, and that the measurements are of the form $\operatorname{sign}(\langle {a}_i, {x} \rangle) \in \{\pm1\}$. Since such measurements give no informati…

This paper resolves BIHT convergence, showing normalization is not necessary in noiseless settings but crucial for robustness.

Robust Lasso-Zero handles missing covariates and sparse corruptions.

The paper proves properties of strain tensors on surfaces with changing Gauss curvature.

This paper improves support recovery in universal one-bit compressed sensing.

Geometric framework for signed multivariate tail-dependence compatibility at various thresholds.

The graph-based semi-supervised label propagation algorithm has delivered impressive classification results. However, the estimated soft labels typically contain mixed signs and noise, which cause inaccurate predictions due to the lack of suitable constraints. Moreover, available methods typically calculate the weights…

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…

This paper improves support recovery in universal one-bit compressed sensing with fewer measurements.

Signed pairwise interactions conflate uniqueness, redundancy, and synergy

It is known that for a certain class of single index models (SIMs) $Y = f(\boldsymbol{X}_{p \times 1}^\intercal\boldsymbolβ_0, \varepsilon)$, support recovery is impossible when $\boldsymbol{X} \sim \mathcal{N}(0, \mathbb{I}_{p \times p})$ and a model complexity adjusted sample size is below a critical threshold. Recen…

New method selects variables in groups with few nonzeros, improving support recovery.

In this paper, we recover sparse signals from their noisy linear measurements by solving nonlinear differential inclusions, which is based on the notion of inverse scale space (ISS) developed in applied mathematics. Our goal here is to bring this idea to address a challenging problem in statistics, \emph{i.e.} finding …

New regularization method corrects over-shrinkage in small data regression.

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

We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) graphical model. The hidden variables follow a tree-structured Ising model distribution, whereas the observable variables are generated by a …

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

Optimal self-distillation improves generative models' velocity risk and mode recovery.

The high-dimensional linear model $y = X β^0 + ε$ is considered and the focus is put on the problem of recovering the support $S^0$ of the sparse vector $β^0.$ We introduce Lasso-Zero, a new $\ell_1$-based estimator whose novelty resides in an "overfit, then threshold" paradigm and the use of noise dictionaries concate…

This paper presents a unified geometric framework for the statistical analysis of a general ill-posed linear inverse model which includes as special cases noisy compressed sensing, sign vector recovery, trace regression, orthogonal matrix estimation, and noisy matrix completion. We propose computationally feasible conv…

The paper proposes a least squares method for binary compressive sampling with low intrinsic dimension signals.

In this paper, we present $\ell_{1,p}$ multi-task structure learning for Gaussian graphical models. We analyze the sufficient number of samples for the correct recovery of the support union and edge signs. We also analyze the necessary number of samples for any conceivable method by providing information-theoretic lowe…

Study 1-bit compressive sensing with generative models, improving recovery accuracy.

Paper tackles phase retrieval with robust gradient descent for noisy data.

The restricted isometry property (RIP) is a universal tool for data recovery. We explore the implication of the RIP in the framework of generalized sparsity and group measurements introduced in the Part I paper. It turns out that for a given measurement instrument the number of measurements for RIP can be improved by o…

Study on signal-plus-noise decomposition in nonlinear spiked random matrices.

Market structure changed dramatically in US during COVID-19, mirroring 2008 crisis.

Sub-gradient method recovers low-rank matrices robustly from noisy measurements.

In this paper we study the support recovery problem for single index models $Y=f(\boldsymbol{X}^{\intercal} \boldsymbolβ,\varepsilon)$, where $f$ is an unknown link function, $\boldsymbol{X}\sim N_p(0,\mathbb{I}_{p})$ and $\boldsymbolβ$ is an $s$-sparse unit vector such that $\boldsymbolβ_{i}\in \{\pm\frac{1}{\sqrt{s}}…

Many problems on signal processing reduce to nonparametric function estimation. We propose a new methodology, piecewise convex fitting (PCF), and give a two-stage adaptive estimate. In the first stage, the number and location of the change points is estimated using strong smoothing. In the second stage, a constrained s…

SELO model predicts link signs better than SDGNN using subgraph encoding and linear optimization.

We argue that the standard graph Laplacian is preferable for spectral partitioning of signed graphs compared to the signed Laplacian. Simple examples demonstrate that partitioning based on signs of components of the leading eigenvectors of the signed Laplacian may be meaningless, in contrast to partitioning based on th…

Novel GNN for signed and directed networks using magnetic signed Laplacian.

A new law limits kurtosis contrast in balanced mixtures.

Sign equivariant networks improve model expressiveness for spectral geometric learning.

Defines signed quasiregular curves and proves growth theorem.

Study on recovering sparse linear classifiers from mixed binary responses.

Signed networks contain both positive and negative kinds of interactions like friendship and enmity. The task of node classification in non-signed graphs has proven to be beneficial in many real world applications, yet extensions to signed networks remain largely unexplored. In this paper we introduce the first analysi…

In this short note, we compare the combinatorial sign assignment of Manolescu, Ozsvath, Szabo and Thurston for grid homology of knots and links in 3-sphere with the sign assignment coming from a coherent system of orientations on Whitney disks. Although these constructions produce different signs, a small modification …

PyTorch Geometric Signed Directed fills the gap for GNNs on signed and directed graphs.

Proposes a privacy-preserving sign selection method for distributed systems.

Estimates graph curvature and diameter using Laplacian eigenvalues.