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.
This work explores the relationship between expressivity and generalization in GNNs.
The margin-based softmax loss functions greatly enhance intra-class compactness and perform well on the tasks of face recognition and object classification. Outperformance, however, depends on the careful hyperparameter selection. Moreover, the hard angle restriction also increases the risk of overfitting. In this pape…
D-CBRS manages memory for continual learning by accounting for intra-class diversity.
Graph filtering reduces intra-class noise for improved classification accuracy.
This paper refines MMD for domain adaptation by balancing intra-class and inter-class distances.
This paper proposes a novel generic one-class feature learning method based on intra-class splitting. In one-class classification, feature learning is challenging, because only samples of one class are available during training. Hence, state-of-the-art methods require reference multi-class datasets to pretrain feature …
The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of deep feature extraction and non-linear feature representation, the clustering algorithm based on deep learning has become a hot research topic in the field of hyperspectral remote s…
Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no more valid in the p…
Person re-identification (Re-ID) aims at matching images of the same person across disjoint camera views, which is a challenging problem in multimedia analysis, multimedia editing and content-based media retrieval communities. The major challenge lies in how to preserve similarity of the same person across video footag…
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domai…
New bounds improve graph node classification using optimal transport.
PortBench benchmarks LLMs for PM, revealing their weaknesses in diversification and robustness.
In this paper, we focus on the separability of classes with the cross-entropy loss function for classification problems by theoretically analyzing the intra-class distance and inter-class distance (i.e. the distance between any two points belonging to the same class and different classes, respectively) in the feature s…
A new loss function HUG decouples and generalizes neural collapse.
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations. Inspired by the observation that CNN-learned features are naturally decoupled with the norm of features corresponding to the intra-class variation and the angle correspond…
This paper proposes a method to use deep neural networks as end-to-end open-set classifiers. It is based on intra-class data splitting. In open-set recognition, only samples from a limited number of known classes are available for training. During inference, an open-set classifier must reject samples from unknown class…
Graph attention improves node classification by distinguishing important edges.
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
Two novel methods improve network embedding for completely-imbalanced labels.
COBRA reduces modality gap in cross-modal tasks.
ECGs improve GNNs for non-homophilic data.
New theory explains contrastive learning via overlapping augmented views.
In this paper we propose the use of multiple local binary patterns(LBPs) to effectively classify land use images. We use the UC Merced 21 class land use image dataset. Task is challenging for classification as the dataset contains intra class variability and inter class similarities. Our proposed method of using multi-…
A new model classifies surface anomalies in 3D point cloud data.
PSC classifier improves HDLSS classification on class-imbalanced data.
AdaCAD improves semi-supervised classification by focusing on intra-class nodes.
Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep representations. To simultaneously achieve these two goals, different solutions h…
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation associated with the labels. The other summarizes the remaining unspecified vari…
Theory for algebraic data on categories via concentration structures.
Paper addresses concentration of distances for fractional quasi p-norms, identifying conditions for concentration and anti-concentration.
Study Finsler metric measure manifolds' concentration properties.
New method improves missing mass concentration bounds.
Surfaces in 3-manifolds concentrate at curvature critical points.
Sharp concentration bounds for i.i.d. variables.
We survey recent results related to the concentration of eigenfunctions. We also prove some new results concerning ball-concentration, as well as showing that eigenfunctions saturating lower bounds for -norms must also, in a measure theoretical sense, have extreme concentration near a geodesic.
A new model CDTM improves text classification by concentrating document topics.
Simplified proof of Gaussian concentration inequality using covariance.
Study provides bounds for estimating intrinsic dimension using Gaussian kernels.
Developed concentrated liquidity in n-dimensional AMM with polar coordinates in Rust.
In this paper, we consider a concentration of measure problem on Riemannian manifolds with boundary. We study concentration phenomena of non-negative -Lipschitz functions with Dirichlet boundary condition around zero, which is called boundary concentration phenomena. We first examine relation between boundary concen…
Study on volume of tubes and concentration in Riemannian geometry.
We introduce a sparse scattering deep convolutional neural network, which provides a simple model to analyze properties of deep representation learning for classification. Learning a single dictionary matrix with a classifier yields a higher classification accuracy than AlexNet over the ImageNet 2012 dataset. The netwo…
Polluting fine dusts in South Korea which are mainly consisted of biomass burning and fugitive dust blown from dust belt is significant problem these days. Predicting concentrations of fine dust particles in Seoul is challenging because they are product of complicate chemical reactions among gaseous pollutants and also…
This study assesses risk concentration in MDB portfolios using Monte Carlo simulations.
We study concentration phenomena of eigenfunctions of the Laplacian on closed Riemannian manifolds. We prove that the volume measure of a closed manifold concentrates around nodal sets of eigenfunctions exponentially. Applying the method of Colding and Minicozzi we also prove restricted exponential concentration inequa…
A limit point p of a discrete group of Mobius transformations acting on S^n is called a concentration point if for any sufficiently small connected open neighborhood U of p, the set of translates of U contains a local basis for the topology of S^n at p. For the case of Fuchsian groups (n = 1), every concentration point…
New approach to concentration inequalities for unbounded state space dynamical systems.
We propose a novel method for automatic pain intensity estimation from facial images based on the framework of kernel Conditional Ordinal Random Fields (KCORF). We extend this framework to account for heteroscedasticity on the output labels(i.e., pain intensity scores) and introduce a novel dynamic features, dynamic ra…