Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

3196399581,277 · Jun 202019922001200920172026
48 results for reciprocal nearest data points

A new hierarchical clustering method selects representative points from sub-minimum-spanning-trees.

problem Selecting representative points for hierarchical clustering to improve robustness and reliability.
method Identify representative points using reciprocal nearest data points in sub-minimum-spanning-trees.
result The proposed algorithm outperforms other methods in accuracy and efficiency.

The study calculates the growth rate of reciprocal hyperbolic elements in Hecke groups.

problem Counting reciprocal hyperbolic elements in Hecke groups.
method Analyzes conjugacy classes of hyperbolic elements associated with reciprocal geodesics.
result Determines the asymptotic growth rate and limiting constant of primitive conjugacy classes of reciprocal hyperbolic elements.

The nearest neighbor problem is defined as follows: Given a set PP of nn points in some metric space (X,D)(X,D), build a data structure that, given any point qq, returns a point in PP that is closest to qq (its "nearest neighbor" in PP). The data structure stores additional information about the set PP, which is th…

2018-06-26abs ↗pdf ↗

Characterizes Lebesgue points using nearest neighbor methods.

problem Consistency of classification algorithms based on nearest neighbors.
method Characterization of Lebesgue points via 1-Nearest Neighbor regression.
result Proves convergence of 1-Nearest Neighbor classification algorithms in metric spaces.

The paper proves generalization bounds and stopping rules for self-selected data in reciprocal learning.

problem Generalization of learning algorithms using self-selected data.
method Proves universal generalization bounds using covering numbers and Wasserstein ambiguity sets.
result Provides stopping rules for reciprocal learning algorithms to ensure out-of-sample performance.

If we pick nn random points uniformly in [0,1]d[0,1]^d and connect each point to its kk-nearest neighbors, then it is well known that there exists a giant connected component with high probability. We prove that in [0,1]d[0,1]^d it suffices to connect every point to cd,1loglogn c_{d,1} \log{\log{n}} points chosen randomly among its $…

2017-11-13abs ↗pdf ↗

A new model predicts network events with improved accuracy and interpretability.

problem Predicting and understanding complex dynamic relational data in networks.
method Mutually Exciting Latent Space Hawkes (LSH) model for continuous-time networks.
result The LSH model outperforms existing models in prediction accuracy and interpretability.

The paper analyzes how much data points can be altered to change their rank in nearest neighbor searches.

problem Vulnerability of nearest neighbor search in high-dimensional data.
method Statistical analysis of perturbation needed to change neighbor rank.
result Derived statistical distribution of perturbation needed to modify neighbor rank.

The paper models reciprocity in interbank markets using a statistical null model.

problem Understanding the importance of individual banks in financial networks.
method Developed an exponential random graph model to account for reciprocal links on both topological and weighted levels.
result Weighted reciprocity in interbank markets is more significant than network size and volume before the financial crisis.

Estimates growth of reciprocal classes in Hecke groups.

problem Estimating the growth of reciprocal conjugacy classes in Hecke groups.
method Using free product structure and word lengths of reciprocal elements, with tools from basic probability theory.
result Estimates the asymptotic growth of reciprocal conjugacy classes in Hecke groups.

The Nearest subspace classifier (NSS) finds an estimation of the underlying subspace within each class and assigns data points to the class that corresponds to its nearest subspace. This paper mainly studies how well NSS can be generalized to new samples. It is proved that NSS is strongly consistent under certain assum…

2015-01-24abs ↗pdf ↗

New method speeds up k-means clustering for large k by improving nearest-neighbor search.

problem Efficiently clustering large datasets with high-dimensional points.
method Seeded Approximate Nearest-Neighbor Search methods to improve Lloyd's algorithm.
result Significantly faster k-means clustering for large k values.

A new ensemble method improves kNN performance by extending the neighborhood rule.

problem Traditional kNN's limitations when test points are outside the spherical region and ensemble's high errors.
method Determines neighbors in k steps, using bootstrap samples and optimal models selection.
result The proposed ensemble method outperforms state-of-the-art methods on 17 benchmark datasets.

In many scientific disciplines structures in high-dimensional data have to be found, e.g., in stellar spectra, in genome data, or in face recognition tasks. In this work we present a novel approach to non-linear dimensionality reduction. It is based on fitting K-nearest neighbor regression to the unsupervised regressio…

2011-07-19abs ↗pdf ↗

This paper proposes a new hashing-based KNN technique for faster nearest neighbor selection.

problem Slowness of KNN in big datasets due to searching entire dataset.
method Divide data space into subcells, use hashing to map data points, and select nearest neighbors layer by layer.
result The proposed technique offers competitive performance with KNN and KDtree while significantly improving time efficiency.

New model accounts for scale variation and noise in pairwise comparisons.

problem Nonreciprocal pairwise comparisons in decision analysis.
method Additive model with structured matrix and random perturbation.
result Explicit estimators and probability assessments of admissible ranking regions.

We consider machine learning in a comparison-based setting where we are given a set of points in a metric space, but we have no access to the actual distances between the points. Instead, we can only ask an oracle whether the distance between two points ii and jj is smaller than the distance between the points ii an…

2017-04-05abs ↗pdf ↗

New topological methods for hypergraph data improve community detection and pattern recognition.

problem Community detection and pattern recognition in hypergraph data.
method Introducing a new topological space structure of hypergraph data, proposing modified nearest neighbors methods.
result Improved methods for community detection and pattern recognition in hypergraph data.

Algorithms often carry out equally many computations for "easy" and "hard" problem instances. In particular, algorithms for finding nearest neighbors typically have the same running time regardless of the particular problem instance. In this paper, we consider the approximate k-nearest-neighbor problem, which is the pr…

2019-02-25abs ↗pdf ↗

Constructs harmonic maps near retractions in hyperbolic spaces.

problem Finding harmonic maps near retractions in hyperbolic spaces.
method Constructs harmonic maps to the hyperbolic plane from quasidisks, and to convex hulls from sets in the boundary at infinity of pinched Hadamard manifolds.
result Harmonic maps are bounded from nearest-point retractions in hyperbolic spaces.

Algorithm identifies nearest mode in noisy data.

problem Identifying the point with the minimum k-th nearest neighbor distance in unknown multivariate probability density.
method Sequential learning algorithm using noisy oracle queries to adaptively decide which points to query.
result Upper bounds on query complexity show significant improvement over baselines.

Study geodesics entering a fixed cusp neighborhood multiple times.

problem Understanding geodesics entering a specific cusp neighborhood multiple times.
method Investigate reciprocal geodesics entering a fixed cusp neighborhood a fixed number of times.
result Characterized the class of reciprocal geodesics entering a fixed cusp neighborhood a fixed number of times.

New method reconstructs interbank networks enforcing reciprocity to improve stability and risk prediction.

problem Lack of public interbank network data and difficulty in replicating cycles.
method Proposes a new network reconstruction method enforcing sparsity and link reciprocity from aggregate data.
result Adding reciprocity improves prediction of network properties, including largest real eigenvalue and eccentricity of eigenvalues.

SPlit optimizes dataset splitting for better model performance.

problem Improving model performance through optimal dataset splitting.
method Adapting Support Points (SP) algorithm for subsampling and categorical variables in a sequential nearest neighbor approach.
result SPlit significantly improves worst-case testing performance compared to random splitting.

The condensed nearest neighbor (CNN) algorithm is a heuristic for reducing the number of prototypical points stored by a nearest neighbor classifier, while keeping the classification rule given by the reduced prototypical set consistent with the full set. I present an upper bound on the number of prototypical points ac…

2013-09-29abs ↗pdf ↗

We explore and expand the Soft Nearest Neighbor Loss\textit{Soft Nearest Neighbor Loss} to measure the entanglement\textit{entanglement} of class manifolds in representation space: i.e., how close pairs of points from the same class are relative to pairs of points from different classes. We demonstrate several use cases of the loss. As an analytical to…

2019-02-05abs ↗pdf ↗

The paper studies empirical processes from nearest neighbors in regression.

problem Estimating conditional cumulative distribution functions and local linear regression.
method Uniform central limit theorem and non-asymptotic bound under local bracketing entropy and uniform entropy numbers.
result Gaussian limit of empirical process with simple covariance.

Proposes a boundary detection method inspired by LLE for high-dimensional data.

problem Identifying boundary points from data on an embedded manifold.
method Inspired by locally linear embedding, uses nearest neighbor search schemes and spectral properties of local covariance matrix.
result Enhanced boundary detection in noisy data.

A new ensemble method using random projections for kNN classification.

problem Improving kNN classification accuracy through ensemble methods.
method Random projection of bootstrap samples into lower dimensions, using extended neighbourhood rule for base learners.
result Enhanced classification accuracy compared to traditional kNN and other ensembles.