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

154308462616 · Jun 202019922001200920172026
48 results for classifier complexity

The paper classifies invariant generalized complex structures on specific flag manifolds.

problem Classifying invariant generalized complex structures on partial flag manifolds.
method Proved that invariant generalized almost complex structures are constant in each component of the isotropy representation.
result All invariant generalized complex structures on partial flag manifolds with at most four isotropy summands are classified.

This paper studies the generalization error of invariant classifiers. In particular, we consider the common scenario where the classification task is invariant to certain transformations of the input, and that the classifier is constructed (or learned) to be invariant to these transformations. Our approach relies on fa…

2016-10-14abs ↗pdf ↗

The paper classifies Hopf hypersurfaces with constant curvatures on complex quadrics.

problem Classifying Hopf hypersurfaces with specific curvature properties.
method Analyzing hypersurfaces on complex quadrics with at most five distinct constant principal curvatures.
result All classified hypersurfaces are open parts of homogeneous examples.

Classifies actions on complex space forms with Lagrangian orbits.

problem Classifying actions on complex space forms with Lagrangian orbits.
method Classifies holomorphic isometric actions on complex space forms.
result Only examples are Lagrangian affine subspace foliations of complex Euclidean spaces and Lagrangian horocycle foliations of complex hyperbolic spaces.

Classifies degenerations of complex projective plane with rational singularities.

problem Classifying singularities of complex projective plane.
method Assuming Wahl's conjecture, classifies degenerations using rational homology disk smoothing.
result Classifies surfaces with rational singularities, including new degenerations with non-log canonical singularities.

We propose a novel combination of optimization tools with learning theory bounds in order to analyze the sample complexity of optimal kernel sum classifiers. This contrasts the typical learning theoretic results which hold for all (potentially suboptimal) classifiers. Our work also justifies assumptions made in prior w…

2019-01-25abs ↗pdf ↗

Algorithm estimates bounds of updated classifier coefficients efficiently.

problem Determining sensitivity of updated classifiers without retraining.
method Proposes an algorithm to estimate upper and lower bounds of updated classifier coefficients.
result Estimates bounds with low computational complexity and tightness.

Current techniques in machine learning are so far are unable to learn classifiers that are robust to adversarial perturbations. However, they are able to learn non-robust classifiers with very high accuracy, even in the presence of random perturbations. Towards explaining this gap, we highlight the hypothesis that $\te…

2019-01-02abs ↗pdf ↗

C-SURE improves complex-valued deep learning models by shrinking estimates, outperforming MLE and SurReal.

problem Improving accuracy and robustness of complex-valued deep learning models.
method Proposes a Stein's unbiased risk estimate (SURE) for complex-valued data and integrates it into a prototype CNN classifier.
result C-SURE outperforms SurReal and MLE in accuracy and robustness on complex-valued datasets.

We study a recent model of collaborative PAC learning where kk players with kk different tasks collaborate to learn a single classifier that works for all tasks. Previous work showed that when there is a classifier that has very small error on all tasks, there is a collaborative algorithm that finds a single classifi…

2018-05-22abs ↗pdf ↗

Classifies meromorphic affine connections on complex surfaces.

problem Investigating uniformization in higher dimensions with singularities.
method Extending work on holomorphic connections, classifying meromorphic connections on compact surfaces.
result Classification of meromorphic affine connections on compact complex surfaces.

The paper classifies complex Dirac structures on flag manifolds.

problem Classifying invariant complex Dirac structures on flag manifolds.
method Described using roots of the Lie algebra and classified under BB-transformations.
result All invariant complex Dirac structures with constant real index on a maximal flag manifold are described.

In this article we study minimal flat Lorentzian surfaces in Lorentzian complex space forms. First we prove that, for minimal flat Lorentzian surfaces in a Lorentzian complex form, the equation of Ricci is a consequence of the equations of Gauss and Codazzi. Then we classify minimal flat Lorentzian surfaces in the Lore…

2013-07-15abs ↗pdf ↗

This paper classifies planar-Rips complexes and their unit disk graphs up to homotopy.

problem Classifying planar-Rips complexes and their unit disk graphs.
method Simplicial classification, homotopy equivalence, and hereditary properties.
result Classification of planar-Rips complexes and unit disk graphs up to homotopy.

The study classifies complex symplectic structures on 4D Lie algebras and constructs hypersymplectic structures.

problem Classifying and constructing complex symplectic structures on 4D Lie algebras.
method Interpreting complex symplectic and pseudo-Kähler structures, developing a method for constructing hypersymplectic structures.
result Obtained an example of a hypersymplectic structure on a 4-step nilmanifold.

The study provides a sample complexity estimate for multi-category classifiers with bounded variation.

problem Controlling the deviation between empirical and generalization performances of multi-category classifiers.
method Using the empirical L1-norm covering number and fat-shattering dimension, the study derives a sample size estimate for classifiers of bounded variation.
result The sample size estimate is sufficient for the performances to be close with high probability, improving the dependency on the number of classes.

Classifies complex symplectic structures on Lie algebras with large abelian ideals.

problem Classifying complex symplectic structures on Lie algebras with large abelian ideals.
method Two constructions of complex symplectic structures on Lie algebras with large abelian ideals, considering compact quotients of Lie groups.
result Complete classification of complex symplectic structures on almost abelian Lie algebras.

New method counts boundary pieces in ReLU classifiers for better complexity measure.

problem Current classification complexity measures are misleading and ineffective.
method Developed a novel method using tropical geometry to count exact boundary pieces.
result Boundary piece count is negatively correlated with robustness.

Researchers classify special curved spheres in a complex space.

problem Classifying special holomorphic two-spheres in a complex Grassmannian.
method Completely classified noncongruent spheres with constant curvature and second fundamental form.
result Found all homogeneous spheres with constant curvature and second fundamental form.

This paper classifies Ricci solitons in complex hyperbolic spaces.

problem Understanding Ricci solitons in complex hyperbolic spaces.
method Analyzing homogeneous expanding Ricci solitons as submanifolds of complex hyperbolic spaces.
result Classification and analysis of Lie subgroups with Ricci soliton induced metric in complex hyperbolic spaces.

Study and classify totally geodesic submanifolds in nearly Kaehler flag manifold.

problem Classifying totally geodesic submanifolds in nearly Kaehler flag manifold.
method Developed structural approach to nearly Kaehler flag manifold, expressed curvature tensor in terms of nearly Kaehler structure and canonical complex structures.
result Classified almost complex totally geodesic submanifolds of nearly Kaehler flag manifold and its semi-Riemannian counterpart.

Classifies and computes cohomologies of complex structures on Lie groups.

problem Classifying and computing cohomologies of complex structures on Lie groups.
method Complete classification and computation of invariant cohomologies for left invariant structures.
result Computed invariant cohomologies for various generalized complex and Kähler structures.

CBC makes CNNs robust against adversarial attacks with minimal computational overhead.

problem Making CNNs robust against adversarial attacks without increasing computational complexity.
method CBC uses a stacked encoder-convolutional model where an auto-encoder encodes the input image, and the latent representation is used for classification.
result CBC is more robust to adversarial examples and has significantly lower computational complexity.

We complete our recent classification of compact inner symmetric spaces with weakly complex tangent bundle by filling up a case which was left open, and extend this classification to the larger category of compact homogeneous spaces with positive Euler characteristic. We show that a simply connected compact equal rank …

2012-02-15abs ↗pdf ↗

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.

Complex Hantzsche-Wendt manifolds are flat Kähler manifolds with holonomy group Z2n1SU(n)\mathbb{Z}_2^{n-1}\subset SU(n). They are important example of Calabi-Yau manifolds of abelian type. In this paper we describe them as quotients of a product of elliptic curves by a finite group G~\tilde{G}. This will allow us to classify…

2015-11-09abs ↗pdf ↗