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.
Deep learning detects cloud changes due to human aerosols.
New method upsamples sparse, non-uniform point clouds more accurately.
A registration-free framework monitors shape and color in 4D point clouds.
Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised learning tasks such as object classification and semantic segmentation. While mas…
Computes bounds on reach and r-convexity from point cloud data.
The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in …
The paper introduces REQNNs for robust 3D point cloud processing.
Method certifies edge predictions with cloud-level reliability.
New method reduces cloud usage for mobile/IoT predictions.
Cluster analysis of very high dimensional data can benefit from the properties of such high dimensionality. Informally expressed, in this work, our focus is on the analogous situation when the dimensionality is moderate to small, relative to a massively sized set of observations. Mathematically expressed, these are the…
3D capsule network for point clouds handles rotations and translations.
New method uses scalar-based models to approximate spherical tensors efficiently.
New methods implement manifold scattering transform for high-dimensional point cloud data.
In this paper, we propose an efficient method to estimate the Weingarten map for point cloud data sampled from manifold embedded in Euclidean space. A statistical model is established to analyze the asymptotic property of the estimator. In particular, we show the convergence rate as the sample size tends to infinity. W…
The Laplace-Beltrami operator (LBO) is a fundamental object associated to Riemannian manifolds, which encodes all intrinsic geometry of the manifolds and has many desirable properties. Recently, we proposed a novel numerical method, Point Integral method (PIM), to discretize the Laplace-Beltrami operator on point cloud…
This paper studies the problem of data-adaptive representations for big, distributed data. It is assumed that a number of geographically-distributed, interconnected sites have massive local data and they are interested in collaboratively learning a low-dimensional geometric structure underlying these data. In contrast …
A new method for computing shape barycenters from point clouds using Procrustes-Wasserstein distance.
New method for high-fidelity shape representations from raw data.
Study shows convergence rates for Cheeger cuts on data clouds.
In this contribution, we present a novel approach for segmenting laser radar (lidar) imagery into geometric time-height cloud locations with a fully convolutional network (FCN). We describe a semi-supervised learning method to train the FCN by: pre-training the classification layers of the FCN with image-level annotati…
In recent decades, the use of 3D point clouds has been widespread in computer industry. The development of techniques in analyzing point clouds is increasingly important. In particular, mapping of point clouds has been a challenging problem. In this paper, we develop a discrete analogue of the Teichmüller extremal mapp…
Framework optimizes cloud container sizing for ML tasks.
Variable importance is central to scientific studies, including the social sciences and causal inference, healthcare, and other domains. However, current notions of variable importance are often tied to a specific predictive model. This is problematic: what if there were multiple well-performing predictive models, and …
This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models. The main idea of the method is to treat a point cloud as a probability density in 3D space that is modeled using a cloud-specific neural network. To capture the similarity between point clouds we rely o…
A new method monitors unstructured 3D shapes without registration.
Paper estimates manifold reach using convexity defect function.
A novel method compresses point cloud attributes by folding them onto a 2D grid.
Clouds frequently cover the Earth's surface and pose an omnipresent challenge to optical Earth observation methods. The vast majority of remote sensing approaches either selectively choose single cloud-free observations or employ a pre-classification strategy to identify and mask cloudy pixels. We follow a different st…
New approach uses distributed persistence for stable, parallelizable topological analysis of large point clouds.
We proposed a novel graph convolutional neural network that could construct a coarse, sparse latent point cloud from a dense, raw point cloud. With a novel non-isotropic convolution operation defined on irregular geometries, the model then can reconstruct the original point cloud from this latent cloud with fine detail…
A novel method compares 3D point clouds using information geometry.
Develops a method for conformal parameterization of point clouds without fixed boundaries.
Improves point-cloud reconstruction by optimizing projections with self-attention.
Algorithm classifies point clouds using deep set linearized optimal transport.
We conduct an empirical study of machine learning functionalities provided by major cloud service providers, which we call machine learning clouds. Machine learning clouds hold the promise of hiding all the sophistication of running large-scale machine learning: Instead of specifying how to run a machine learning task,…
Cumulo dataset for cloud classification at 1km resolution.
This paper analyzes CNNs for malware detection in cloud IaaS.
Estimating boundaries from point clouds with improved accuracy and rigorous error estimates.
The increasing demand for on-device deep learning services calls for a highly efficient manner to deploy deep neural networks (DNNs) on mobile devices with limited capacity. The cloud-based solution is a promising approach to enabling deep learning applications on mobile devices where the large portions of a DNN are of…
Point cloud is the most fundamental representation of 3D geometric objects. Analyzing and processing point cloud surfaces is important in computer graphics and computer vision. However, most of the existing algorithms for surface analysis require connectivity information. Therefore, it is desirable to develop a mesh st…
We present a technique for efficiently synthesizing images of atmospheric clouds using a combination of Monte Carlo integration and neural networks. The intricacies of Lorenz-Mie scattering and the high albedo of cloud-forming aerosols make rendering of clouds---e.g. the characteristic silverlining and the "whiteness" …
SPINN optimizes neural network inference on devices and cloud.
Optimal Transport Graph Neural Networks (OT-GNN) improves graph embeddings by using optimal transport.
The paper transforms a convex hull into a concave surface around a point cloud.
Geometric Capsule Autoencoders group 3D points into parts and objects.
Paper proposes a hierarchical approach to malware detection in cloud environments.
Deep learning identifies precipitation clouds from all-sky camera data.
In the following article we discuss Delaunay triangulations for a point cloud on an embedded surface in . We give sufficient conditions on the point cloud to show that the diagonal switch algorithm finds an embedded Delaunay triangulation.