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.
CP-GAN generates images selectively conditioned on class specificity, capturing between-class relationships.
Deep learning methods have achieved high performance in sound recognition tasks. Deciding how to feed the training data is important for further performance improvement. We propose a novel learning method for deep sound recognition: Between-Class learning (BC learning). Our strategy is to learn a discriminative feature…
Distilled teacher model transfers knowledge to student model on new datasets.
In this paper, we propose a novel learning method for image classification called Between-Class learning (BC learning). We generate between-class images by mixing two images belonging to different classes with a random ratio. We then input the mixed image to the model and train the model to output the mixing ratio. BC …
Class selectivity affects robustness to corruptions but not to adversarial attacks.
A new neural network learns from acoustic scenes by suppressing irrelevant patterns.
Fisher loss improves deep domain adaptation by learning discriminative within-class compact and between-class separable representations.
Nodes in real world networks often have class labels, or underlying attributes, that are related to the way in which they connect to other nodes. Sometimes this relationship is simple, for instance nodes of the same class are may be more likely to be connected. In other cases, however, this is not true, and the way tha…
Deep neural networks (DNNs) have achieved exceptional performances in many tasks, particularly, in supervised classification tasks. However, achievements with supervised classification tasks are based on large datasets with well-separated classes. Typically, real-world applications involve wild datasets that include si…
TzK model learns from multiple datasets efficiently.
SWRLDA improves LDA for multi-class classification with edge classes.
This paper is devoted to the systematic investigation of the cone construction for Riemannian manifolds M, endowed with an invariant metric connection with skew torsion , a `characteristic connection'. We show how to define a structure on the cone $\bar M=M\x \R^+$ with a cone metric, and we prov…
Maximizes coding rate difference for robust, discriminative features.
Nonnegative Matrix Factorization (NMF) has been a popular representation method for pattern classification problem. It tries to decompose a nonnegative matrix of data samples as the product of a nonnegative basic matrix and a nonnegative coefficient matrix, and the coefficient matrix is used as the new representation. …
A framework learns dynamic soft labels to improve model generalization and accuracy.
A new data augmentation method selects mixed classes based on class distances for better performance.
A number of classification problems need to deal with data imbalance between classes. Often it is desired to have a high recall on the minority class while maintaining a high precision on the majority class. In this paper, we review a number of resampling techniques proposed in literature to handle unbalanced datasets …
Novel L1-norm and L2-norm LDA methods improve discriminant analysis.
Extends L2-norm LDA to 2D inputs using Bhattacharyya bound.
A new DR method for HSI classification improves accuracy with limited samples.
CCCDs tackle class imbalance in classification.
This work investigates how neural collapse improves transfer learning for large-scale models.
Paper optimizes classification of distributions using Wasserstein metric.
Optimizes natural frequencies of cellular composites with various microstructures.
We present a graph-based variational algorithm for multiclass classification of high-dimensional data, motivated by total variation techniques. The energy functional is based on a diffuse interface model with a periodic potential. We augment the model by introducing an alternative measure of smoothness that preserves s…
Sharp-SSL uses random projections to identify important variables for semi-supervised learning.
A novel supervised visualization technique for data exploration.
Exploits class similarity for better machine learning models with confidence labels and projective loss functions.
The study finds conditions for positive braid knots to be Gordian adjacent and explores their unknotting sequences.
Machine learning detects and classifies cognitive distortions in mental health texts.
Learning high quality class representations from few examples is a key problem in metric-learning approaches to few-shot learning. To accomplish this, we introduce a novel architecture where class representations are conditioned for each few-shot trial based on a target image. We also deviate from traditional metric-le…
This report works out the details of a closed-form, fully Bayesian, multiclass, openset, generative pattern classifier using multivariate Gaussian likelihoods, with conjugate priors. The generative model has a common within-class covariance, which is proportional to the between-class covariance in the conjugate prior. …
Collective classification models attempt to improve classification performance by taking into account the class labels of related instances. However, they tend not to learn patterns of interactions between classes and/or make the assumption that instances of the same class link to each other (assortativity assumption).…
In this paper, we propose a new framework to study the generalization property of classifier chains trained over observations associated with multiple and interdependent class labels. The results are based on large deviation inequalities for Lipschitz functions of weakly dependent sequences proposed by Rio in 2000. We …
We present a graph-based variational algorithm for classification of high-dimensional data, generalizing the binary diffuse interface model to the case of multiple classes. Motivated by total variation techniques, the method involves minimizing an energy functional made up of three terms. The first two terms promote a …
Proposes a new loss function for distributional learning.
We address the problem of semi-supervised learning in relational networks, networks in which nodes are entities and links are the relationships or interactions between them. Typically this problem is confounded with the problem of graph-based semi-supervised learning (GSSL), because both problems represent the data as …
Kernel alignment measures the degree of similarity between two kernels. In this paper, inspired from kernel alignment, we propose a new Linear Discriminant Analysis (LDA) formulation, kernel alignment LDA (kaLDA). We first define two kernels, data kernel and class indicator kernel. The problem is to find a subspace to …
01 loss is robust to outliers and adversarial attacks, outperforming convex losses.
New method visualizes decision boundaries of classification models.
Paper analyzes classical multidimensional scaling for cluster recovery.
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize…
We study prediction and estimation problems using empirical risk minimization, relative to a general convex loss function. We obtain sharp error rates even when concentration is false or is very restricted, for example, in heavy-tailed scenarios. Our results show that the error rate depends on two parameters: one captu…
To date, testing interactions in high dimensions has been a challenging task. Existing methods often have issues with sensitivity to modeling assumptions and heavily asymptotic nominal p-values. To help alleviate these issues, we propose a permutation-based method for testing marginal interactions with a binary respons…
Paper proposes a new loss function for PU learning without negative examples.
Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish such models and present a novel neural network architecture for the task of weakly…
BO method improved by density-ratio estimation for better efficiency and scalability.
New metric assesses image dataset complexity.