Study on error probability for classification of heavy-tailed renewal processes.
problem Error probability in classification of heavy-tailed renewal processes.
method Asymptotic expressions for Bhattacharyya bound on misclassification error probabilities.
result Obtained asymptotic expressions for misclassification error probabilities.
Study classifies 4D Ricci solitons with specific curvature conditions.
problem Classifying 4D gradient steady and expanding Ricci solitons with given curvature properties.
method Asymptotically cylindrical and conical assumptions; half-harmonic and half-nonnegative isotropic curvature conditions.
result Partial classification of 4D gradient expanding Ricci solitons with half-nonnegative isotropic curvature.
Classifies 2-uniform maps on torus with formulas and asymptotic bounds.
problem Classifying 2-uniform maps on torus.
method Classification through arithmetic functions and asymptotic analysis.
result Explicit formulas and asymptotic bounds for 2-uniform maps on torus.
Paper analyzes multiclass classification with high-dimensional data.
problem Understanding statistical properties and behavior of multiclass classification algorithms.
method Asymptotic analysis of linear multiclass classification.
result Test error varies significantly across different training algorithms and data distributions.
We present a classification of SU(2) instantons on T2×R2 according to their asymptotic behaviour. We then study the existence of such instantons for different values of the asymptotic parameters, describing explicitly the moduli space for unit charge.
Corrected proof for 3D harmonic manifolds with minimal horospheres.
problem Proving 3D harmonic manifolds with minimal horospheres are either flat or hyperbolic.
method Provided a corrected proof for the classification of 3D harmonic manifolds.
result Classification of 3D harmonic manifolds: flat or hyperbolic.
We introduce a geometric property complementary-finite asymptotic dimension (coas- dim). Similar with asymptotic dimension, we prove the corresponding coarse invariant theorem, union theorem and Hurewicz-type theorem.
We classify noncompact homogeneous spaces which are Einstein and asymptotically harmonic. This completes the classification of Riemannian harmonic spaces in the homogeneous case: Any simply connected homogeneous harmonic space is flat, or rank-one symmetric, or a nonsymmetric Damek-Ricci space. Independently, Y. Nikola…
The paper proves asymptotic normality for multinomial logistic regression on null covariates.
problem Classical asymptotic normality results fail in high-dimensional multinomial logistic models.
method Developed asymptotic normality and chi-square results for multinomial logistic MLE on null covariates.
result Validated new methodology to test feature significance in high-dimensional classification problems.
Study resolves conjecture on overparameterized linear models' generalization.
problem Asymptotic generalization of multiclass classification with overparameterized models.
method Gaussian covariates bi-level model, Hanson-Wright inequality variant.
result Min-norm interpolating classifier can be suboptimal compared to noninterpolating classifiers.
New classifiers converge under large data, simplifying complex models.
problem Complex predictive models under large datasets.
method Convergence of simultaneous and marginal classifiers under partition exchangeability.
result Asymptotic convergence of classifiers with large data reduces computational complexity.
Optimal downsampling improves GLM performance in imbalanced classification.
problem Improving GLM performance in imbalanced classification.
method Proposed a pseudo maximum likelihood estimator for optimal downsampling.
result The introduced estimator outperforms existing alternatives in both synthetic and empirical data.
Enhances graph classification with multiple graphs.
problem Improving graph classification accuracy with multiple graphs.
method Graph fusion embedding using encoder embedding.
result The method consistently improves classification accuracy for large vertex sets.
Motivated by the study of Fano type varieties we define a new class of log pairs that we call asymptotically log Fano varieties and strongly asymptotically log Fano varieties. We study their properties in dimension two under an additional assumption of log smoothness, and give a complete classification of two dimension…
Optimal graph classification uses message-passing neural networks.
problem Node classification on sparse graphs with fixed feature dimensions.
method Asymptotic local Bayes optimality, message-passing graph neural networks.
result Optimal message-passing architecture interpolates between MLP and convolution.
The study characterizes learning Gaussian mixtures using GLMs in high dimensions.
problem Learning Gaussian mixtures with generalised linear models in high-dimensional settings.
method Empirical risk minimization with convex loss and regularisation.
result Exact asymptotics of the ERM estimator for Gaussian mixtures in high dimensions.
This paper classifies solutions for a specific geometric problem.
problem Classifying solutions for the planar isotropic Lp dual Minkowski problem. method Converted the ODE for the solution into an integral and studied its asymptotic behavior, duality, and monotonicity.
result Complete classification of solutions for the equation.
This paper classifies Calabi-Yau manifolds near cones.
problem Classifying Calabi-Yau manifolds near cones.
method Complete classification of smooth complete Calabi-Yau manifolds asymptotic to a given cone.
result Classification of all smooth complete Calabi-Yau manifolds near a given cone.
Classifies and constructs translators for curvature flows.
problem Understanding translating solitons in curvature flows.
method Developed rotational theory, introduced signed-neck framework.
result Classified and constructed catenoidal-type translators.
We investigate asymptotically flat manifolds with cone structure at infinity. We show that any such manifold M has a finite number of ends. For simply connected ends we classify all possible cones at infinity, except for the 4-dimensional case where it remains open if one of the theoretically possible cones can actuall…
Study of 4D Ricci solitons with symmetry, finding precise geometric asymptotics.
problem Classifying 4D gradient steady Ricci solitons and understanding their geometric properties.
method Analysis of 4D gradient steady Ricci solitons with O(3)-symmetry under a weak curvature decay condition.
result Find precise geometric asymptotics similar to 3D compact κ-solutions.
We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for conditional dependencies across words in a document), they have higher asymptoti…
Study on error probabilities of machine learning classification techniques using large deviations theory.
problem Performance analysis of machine learning binary classification techniques.
method Large deviations theory applied to Data-Driven Decision Function (D3F) for error probability analysis.
result Classification error probabilities vanish exponentially, with an asymptotic formula providing precise error rate estimates.
A good classification method should yield more accurate results than simple heuristics. But there are classification problems, especially high-dimensional ones like the ones based on image/video data, for which simple heuristics can work quite accurately; the structure of the data in such problems is easy to uncover wi…
We study compact stable embedded minimal surfaces whose boundary is given by two collections of closed smooth Jordan curves in close planes of Euclidean 3-space. Our main result is a classification of these minimal surfaces, under certain natural geometric asymptotic constraints, in terms of certain associated varifold…
Paper analyzes adversarial training's performance in binary classification.
problem Understanding the generalization performance of adversarial training.
method Derives precise theoretical predictions for adversarial training performance.
result Provides exact asymptotics for test errors of adversarial training.
The study classifies certain types of incomplete surfaces with low curvature.
problem Classifying incomplete affine spheres with specific curvature constraints.
method Analyzing total curvature and asymptotic behavior of surfaces.
result New examples of incomplete affine spheres with positive genus found.
New findings on κ-solutions with round cylinder as asymptotic shrinker.
problem Characterizing κ-solutions with specific asymptotic behavior. method Analysis of Ricci flow in dimensions n≥4. result Uniformly Positive Isoperimetric Constant (PIC) for κ-solutions. Unique asymptotics found for special geometric flows.
problem Classifying ancient ovals of Ricci flow.
method Analyzing invariant, compact, non-self-similar solutions.
result Uniqueness of the profile function G(z,t). Work in the classification literature has shown that in computing a classification function, one need not know the class membership of all observations in the training set; the unlabeled observations still provide information on the marginal distribution of the feature set, and can thus contribute to increased classifi…
This is the second article of a series or two, proving a generalisation of the uniqueness theorem of the Schwarzschild solution. The theorem to be shown classifies all (metrically complete) solutions of the static vacuum Einstein equations with compact but non-necessarily connected horizon without any further assumptio…
Prove rigidity and classification results for quasilinear Liouville equation on manifolds with nonnegative Ricci curvature.
problem Quasilinear Liouville equation on manifolds with nonnegative Ricci curvature.
method Prove rigidity and classification results for the quasilinear Liouville equation associated with the n-Laplacian on complete noncompact Riemannian manifolds with nonnegative Ricci curvature. result Under a sharp logarithmic lower bound, the ambient manifold must be isometric to the Euclidean space and the solution must be one of the standard bubbles.
New method improves model risk prediction using cross-audit projection.
problem Over-optimism in K-fold CV for binary classification. method Cross-audit projection (CAP) procedure combining resampling and asymptotic bias correction.
result CAP estimator achieves second-order asymptotic unbiasedness.
Extends graph encoder embedding to weighted graphs and matrices.
problem Classifying vertices in various graph types efficiently.
method Graph encoder embedding applied to weighted graphs, distance matrices, and kernel matrices.
result The method achieves asymptotic normality, enabling optimal classification.
Study asymptotic behavior of translators in hyperbolic product space.
problem Classify asymptotic boundary components of translators in H2imesR. method Inspired by earlier work on minimal and constant mean curvature surfaces, use symmetric translators as barriers.
result Prove classification of asymptotic boundary components under continuity assumptions.
The paper develops a statistical theory explaining overfitting in imbalanced classification.
problem Overfitting in high-dimensional imbalanced classification.
method Developed a statistical theory for support vector machines and logistic regression.
result Overfitting is more severe for the minority class due to truncation or skewing effects in high-dimensional data.
Margin-based classifiers have been popular in both machine learning and statistics for classification problems. Since a large number of classifiers are available, one natural question is which type of classifiers should be used given a particular classification task. We answer this question by investigating the asympto…
The article compares predictor importance in classification problems with categorical outcomes.
problem Comparing predictor importance in classification problems with categorical response variables.
method The approach is based on the categorical Gini correlation (CGC) and tests differences in CGCs across predictor groups.
result The proposed methodology accommodates predictors of arbitrary and unequal dimensions and allows for dependence between predictor groups.
New findings show Gaussian universality breaks down in high-dimensional linear factor mixtures.
problem The limitations of Gaussian universality in high-dimensional classification.
method Characterization of empirical risk minimization for classification under linear factor mixture models.
result Gaussian universality breaks down under high-dimensional linear factor mixtures.
Geometric arguments show simplicial arrangements with few double points can't have an irreducible cubic curve dual.
problem Classifying simplicial arrangements with a linear bound on double points.
method Geometric arguments and structure theorem from Green and Tao.
result Simplicial arrangements with few double points can't have an irreducible cubic curve dual.
Study Liouville equation on Riemannian surfaces, linking volume growth to classification results.
problem Classifying solutions and manifolds of the Liouville equation on Riemannian surfaces.
method Analyzing the Liouville equation −Δu=eu on Riemannian surfaces with non-negative Ricci curvature, considering asymptotic volume growth. result Established classification results for solutions and manifolds, revealing a connection between volume growth and classification.
A new method uses SVM classification to efficiently compute confidence sets.
problem Computing confidence sets for moment inequalities is computationally intensive.
method Converts confidence set construction into a classification problem using SVM.
result Asymptotically reproduces the test in the confidence set using SVM classification.
We prove a necessary and sufficient condition for an asymptotically Euclidean manifold to be conformally related to one with specified nonpositive scalar curvature: the zero set of the desired scalar curvature must have a positive Yamabe invariant, as defined in the article. We show additionally how the sign of the Yam…
This paper explores charged black holes in 3+1 dimensions, finding limitations on their existence.
problem Classifying charged electrostatic black holes in arbitrary topology.
method Comparison geometry techniques.
result Charged Schwarzschild black holes are possible, but not Boosts or Myers-Korotkin-Nicolai solutions.
In this letter, we derive the optimal discriminant functions for modulation classification based on the sampled distribution distance. The proposed method classifies various candidate constellations using a low complexity approach based on the distribution distance at specific testpoints along the cumulative distributi…
Classifies ancient ovals in higher dimensional mean curvature flow.
problem Classifying ancient ovals in higher dimensional mean curvature flow.
method Spectral parametrization to classify k-ovals.
result Classifies k-ovals in arbitrary dimensions.
Sharp bounds on binary model inference performance.
problem High-dimensional inference in binary models.
method Convex empirical risk minimization, sharp asymptotics, optimal performance bounds.
result Sharp predictions and optimal performance bounds for binary models.
Method predicts multistable system states from sparse measurements.
problem Predicting multistable system states from limited data.
method Semi-supervised classification with SPML optimization.
result 95% accuracy in predicting reaction-diffusion equation states.