# Matching Map Recovery with an Unknown Number of Outliers

@article{Minasyan2022MatchingMR, title={Matching Map Recovery with an Unknown Number of Outliers}, author={Arshak Minasyan and Tigran Galstyan and S. A. Hunanyan and Arnak S. Dalalyan}, journal={ArXiv}, year={2022}, volume={abs/2210.13354} }

We consider the problem of ﬁnding the matching map between two sets of d -dimensional noisy feature-vectors. The distinctive feature of our setting is that we do not assume that all the vectors of the ﬁrst set have their corresponding vector in the second set. If n and m are the sizes of these two sets, we assume that the matching map that should be recovered is deﬁned on a subset of unknown cardinality k ∗ ≤ min( n, m ) . We show that, in the high-dimensional setting, if the signal-to-noise…

## References

SHOWING 1-10 OF 59 REFERENCES

### One-Way Matching of Datasets with Low Rank Signals

- Computer ScienceArXiv
- 2022

Under a stylized model, it is shown that linear assignment with projected data achieves fast rates of convergence and sometimes even minimax rate optimality for this task.

### Maximum Flow and Minimum-Cost Flow in Almost-Linear Time

- Computer Science, Mathematics2022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS)
- 2022

We give an algorithm that computes exact maximum flows and minimum-cost flows on directed graphs with m edges and polynomially bounded integral demands, costs, and capacities in $m^{1+o(1)}$ time.…

### Optimal detection of the feature matching map in presence of noise and outliers

- Computer Science, MathematicsElectronic Journal of Statistics
- 2022

The main result shows that, in the high-dimensional setting, a detection region of unknown injection may be characterized by the sets of vectors for which the inlier-inlier distance is of order at least d 1 / 4 and theInlier-outlier distance

### Minimax Rates in Permutation Estimation for Feature Matching

- Computer ScienceJ. Mach. Learn. Res.
- 2016

The problem of matching two sets of features appears in various tasks of computer vision and can be often formalized as a problem of permutation estimation and a theoretical analysis of the accuracy of several natural estimators is provided.

### SCANPY: large-scale single-cell gene expression data analysis

- Computer Science, BiologyGenome Biology
- 2018

This work presents Scanpy, a scalable toolkit for analyzing single-cell gene expression data that includes methods for preprocessing, visualization, clustering, pseudotime and trajectory inference, differential expression testing, and simulation of gene regulatory networks, and AnnData, a generic class for handling annotated data matrices.

### Random Graph Matching in Geometric Models: the Case of Complete Graphs

- Computer Science, MathematicsCOLT
- 2022

An approximate maximum likelihood estimator is derived, which provably achieves, with high probability, perfect recovery of π ∗ when σ = o ( n − 2 /d ) and almost perfect recovery with a vanishing fraction of errors when ρ = n − 1 /d .

### Matrix Reordering for Noisy Disordered Matrices: Optimality and Computationally Efficient Algorithms

- Computer Science
- 2022

This work first establishes the fundamental statistical limit for the matrix reordering problem in a decision-theoretic framework and shows that a constrained least square estimator is rate-optimal, and proposes a novel polynomial-time adaptive sorting algorithm.

### Localization in 1D non-parametric latent space models from pairwise affinities

- Computer Science
- 2021

An estimation procedure is introduced that provably localizes all the latent positions in a one-dimensional torus with a maximum error of the order of √ log(n)/n, with highprobability, and is proven to be minimax optimal.

### Strong recovery of geometric planted matchings

- Mathematics, Computer ScienceSODA
- 2022

The problem of efficiently recovering the matching between an unlabelled collection of n points in R and a small random perturbation of those points is studied and it is shown that the MLE makes n errors for an explicit δ ∈ (0, 1).