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.
Enhances mixture models with classifier-defined weights.
The first Betti number for a lattice in a classifying space for variations of Hodge structures vanishes.
The paper classifies and studies conformal variations of submanifolds.
This paper analyzes -Variational Classifiers for robustness and adversarial perturbation detection.
The study provides a sample complexity estimate for multi-category classifiers with bounded variation.
Discriminative classifier for compositional data using hierarchical mixture of Generalized Dirichlet models.
Mutual information bounds generalization error in variational classifiers.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performan…
GMVAE improves open-set classification by clustering latent representations.
Learning binary classifiers only from positive and unlabeled (PU) data is an important and challenging task in many real-world applications, including web text classification, disease gene identification and fraud detection, where negative samples are difficult to verify experimentally. Most recent PU learning methods …
We investigate variations of Brieskorn lattices over non-compact parameter spaces, and discuss the corresponding limit objects on the boundary divisor. We study the associated variation of twistors and the corresponding limit mixed twistor structures. We construct a compact classifying space for regular singular Briesk…
Quantum model improves safety in machine learning.
A new method estimates mutual information using neural classifiers.
The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a distribution. Here, we propose an extension of the VAE framework that incorporates a classi…
Classifies soap film surfaces with vertical potentials.
UKM framework optimizes VQCs, showing QCL performance is bounded.
Paper uses non-Euclidean analysis to classify brain structure variations.
A smaller, less-trained model guides image generation, improving quality without sacrificing variation.
Enhances classification accuracy on low data sets using synthetic data.
Geometric variations of objects, which do not modify the object class, pose a major challenge for object recognition. These variations could be rigid as well as non-rigid transformations. In this paper, we design a framework for training deformable classifiers, where latent transformation variables are introduced, and …
Variational methods have been recently considered for scaling the training process of Gaussian process classifiers to large datasets. As an alternative, we describe here how to train these classifiers efficiently using expectation propagation. The proposed method allows for handling datasets with millions of data insta…
IntroVAC learns interpretable latent subspaces for better image quality.
DIVA clusters dynamic data without needing cluster count, outperforming baselines.
The paper classifies surfaces with constant skew curvature in 3-space forms.
It is common that a trained classification model is applied to the operating data that is deviated from the training data because of noise. This paper demonstrates that an ensemble classifier, Diversified Multiple Tree (DMT), is more robust in classifying noisy data than other widely used ensemble methods. DMT is teste…
A new framework for neural network classification using vector quantization.
Study area-minimizing subgraphs in integer lattices.
The paper classifies Landsberg spherically symmetric Finsler metrics in various dimensions.
We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to humans: identity in faces, objects in images, and utterances in speech. We propose …
New method classifies hypersurfaces that can bend infinitesimally.
Improved reliability of machine learning predictions using variational auto-encoders.
We apply the network Lasso to classify partially labeled data points which are characterized by high-dimensional feature vectors. In order to learn an accurate classifier from limited amounts of labeled data, we borrow statistical strength, via an intrinsic network structure, across the dataset. The resulting logistic …
Lower bounds show learning mixtures of linear classifiers is nearly impossible.
ProBoost boosts probabilistic classifiers by focusing on uncertain samples.
Several numerical approximation strategies for the expectation-propagation algorithm are studied in the context of large-scale learning: the Laplace method, a faster variant of it, Gaussian quadrature, and a deterministic version of variational sampling (i.e., combining quadrature with variational approximation). Exper…
Deep learning reconstructs pressure fields and classifies leakage rates in CCS storage sites.
This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-cla…
In this draft, which reports on work in progress, we 1) adapt the information bottleneck functional by replacing the compression term by class-conditional compression, 2) relax this functional using a variational bound related to class-conditional disentanglement, 3) consider this functional as a training objective for…
This study improves quantum classifiers by optimizing data preprocessing.
New classification of 5D nilsolitons using algebraic Ricci soliton equation.
Study proves existence of robust classifiers in multiclass adversarial training.
A complete solution to the multiplier version of the inverse problem of the calculus of variations is given for a class of hyperbolic systems of second-order partial differential equations in two independent variables. The necessary and sufficient algebraic and differential conditions for the existence of a variational…
Study of deformations of Virasoro symmetries using variational bihamiltonian cohomology.
Voxelwise classification approaches are popular and effective methods for tissue quantification in brain magnetic resonance imaging (MRI) scans. However, generalization of these approaches is hampered by large differences between sets of MRI scans such as differences in field strength, vendor or acquisition protocols. …
We calculate the first and the second variation formula for the sub-Riemannian area in three dimensional pseudo-hermitian manifolds. We consider general variations that can move the singular set of a C^2 surface and non-singular variation for C_H^2 surfaces. These formulas enable us to construct a stability operator fo…
Classifies solutions in multisymplectic field theories using geometric gauge freedom.
We develop techniques for classifying the nonnegatively curved left-invariant metrics on a compact Lie group G. We prove rigidity theorems for general G and a partial classification for G=SO(4). Our approach is to reduce the general question to an infinitesimal version; namely, to classify the directions one can move a…
The paper finds local minimizers for obstacle avoidance on curved spaces.