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.
New method uses graph generative models for graph classification.
We study realizations of Lie algebras by vector fields. A correspondence between classification of transitive local realizations and classification of subalgebras is generalized to the case of regular local realizations. A reasonable classification problem for general realizations is rigorously formulated and an algori…
CNNs improve generalization to unseen audio devices with increased width, not depth.
The paper analyzes how overparameterized models can generalize well in multiclass classification.
The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
Proposes a new framework for image generation using classification latent space representations.
Classifies generalized Seifert fiber spaces and their branched covers.
We develop a novel probabilistic generative model based on the variational autoencoder approach. Notable aspects of our architecture are: a novel way of specifying the latent variables prior, and the introduction of an ordinality enforcing unit. We describe how to do supervised, unsupervised and semi-supervised learnin…
It is given the diffeomorphism classification on generic singularities of tangent varieties to curves with arbitrary codimension in a projective space. The generic classifications are performed in terms of certain geometric structures and differential systems on flag manifolds, via several techniques in differentiable …
In this paper, we present the classification of generalized Wallach spaces and discuss some related problems.
Paper develops MRCs for supervised classification using generalized maximum entropy.
It is well known that the classification of the Weyl tensor in Lorentzian manifolds of dimension four, the so called Petrov classification, was a great tool to the development of general relativity. Using the bivector approach it is shown in this article a classification for the Weyl tensor in all four-dimensional mani…
The study examines generalization bounds for regression and classification tasks on adaptive input domains.
Machine learning reveals hidden features in knot classification.
Paper proposes fully Bayesian approach for RVM classification, improving accuracy especially in imbalanced data.
Simplicial learning improves classification by generating compact sparse representations.
Score-based generative models achieve state-of-the-art classification accuracy on CIFAR-10.
Classifies and computes cohomologies of complex structures on Lie groups.
MAGIC-Flow generates and classifies medical images with interpretability.
Sequence classification is an important data mining task in many real world applications. Over the past few decades, many sequence classification methods have been proposed from different aspects. In particular, the pattern-based method is one of the most important and widely studied sequence classification methods in …
Generative model evaluates text emotion intensity, outperforming classification.
Paper interprets ResNets via gate-network controls and deep-layer classifications.
We give a full proof to Agol's announcement on the classification of non-free Kleinian groups generated by two parabolic transformations.
We give a classification of generic bifurcations of intersections of wavefronts generated by different points of a hypersurface with or without boundaries.
Optimal downsampling improves GLM performance in imbalanced classification.
Author2Vec generates user embeddings from social media data.
Recent metric-based meta-learning approaches, which learn a metric space that generalizes well over combinatorial number of different classification tasks sampled from a task distribution, have been shown to be effective for few-shot classification tasks of unseen classes. They are often trained with episodic training …
Without any specific way for imbalance data classification, artificial intelligence algorithm cannot recognize data from minority classes easily. In general, modifying the existing algorithm by assuming that the training data is imbalanced, is the only way to handle imbalance data. However, for a normal data handling, …
Conventional techniques for supervised classification constrain the classification rules considered and use surrogate losses for classification 0-1 loss. Favored families of classification rules are those that enjoy parametric representations suitable for surrogate loss minimization, and low complexity properties suita…
Paper tackles leveraging unlabeled data for PU classification and robust generation.
Proposes MGCE for improved classification performance.
Enhances graph classification models on small datasets.
Study on continuous sequence classification with distribution uncertainty.
We note that a rational -tangle diagram is obtained from a combination of four generators. There is an algorithm to distinguish two rational -tangle diagrams up to isotopy. However, there is no perfect classification about rational -tangle diagrams such as the classification of rational -tangle diagrams cor…
We survey the existing parts of a classification of finite groups generated by orthogonal transformations in a finite-dimensional Euclidean space whose fixed point subspace has codimension one or two and extend it to a complete classification. These groups naturally arise in the study of the quotient of a Euclidean spa…
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…
New NHCAs improve multi-category classification efficiency.
Establishes a condition for multiclass classification-calibration of Gamma-Phi losses.
With the advents of deep learning, improved image classification with complex discriminative models has been made possible. However, such deep models with increased complexity require a huge set of labeled samples to generalize the training. Such classification models can easily overfit when applied for medical images …
Neural NCD reveals LLMs don't compress well for classification.
Sharp bounds on uniform generalization errors in binary linear classification.
This research improves PAC-Bayesian bounds for classification tasks using convexified loss.
Recent work has shown that exploiting relations between labels improves the performance of multi-label classification. We propose a novel framework based on generative adversarial networks (GANs) to model label dependency. The discriminator learns to model label dependency by discriminating real and generated label set…
Recent advances in large-margin classification of data residing in general metric spaces (rather than Hilbert spaces) enable classification under various natural metrics, such as string edit and earthmover distance. A general framework developed for this purpose by von Luxburg and Bousquet [JMLR, 2004] left open the qu…
We give a local classification of generalized complex structures. About a point, a generalized complex structure is equivalent to a product of a symplectic manifold with a holomorphic Poisson manifold. We use a Nash-Moser type argument in the style of Conn's linearization theorem.
Unified principle LZN unifies generative modeling, representation learning, and classification.
Deep neural networks classify unbounded Gaussian mixture data without dimensionality issues.
This paper improves binary classification methods beyond accuracy, especially in imbalanced datasets.