arXiv research

Solar improves variable selection in high-dimensional data with complicated dependence structures.

Let $M$ be a 3-manifold with torus boundary components $T_1$ and $T_2$. Let $φ\colon T_1 \to T_2$ be a homeomorphism, $M_φ$ the manifold obtained from $M$ by gluing $T_1$ to $T_2$ via the map $φ$, and $T$ the image of $T_1$ in $M_φ$. We show that if $φ$ is "sufficiently complicated" then any incompressible or strongly …

Structured missing data complicates machine learning, presenting new challenges.

Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures. The main reason is that most of the current generative models fail to explore the structures in the images including spatial layout and semantic relations betwe…

Centripetal SGD prunes deep CNNs by making filters collapse.

Motivated by the algorithmic study of 3-dimensional manifolds, we explore the structural relationship between the JSJ decomposition of a given 3-manifold and its triangulations. Building on work of Bachman, Derby-Talbot and Sedgwick, we show that a "sufficiently complicated" JSJ decomposition of a 3-manifold enforces a…

We provide a diagrammatic criterion for semi-adequate links to be hyperbolic. We also give a conjectural description of the satellite structures of semi-adequate links. One application of our result is that the closures of sufficiently complicated positive braids are hyperbolic links.

Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern transportation management. The complicated spatial dependencies of roadway links and the dynamic temporal patterns of traffic states make it particularly challenging. To address these challenges, we propos…

Study describes severe dengue ICU patients in Brazil, 2012-2024.

Smooth SE structures on Sasaki-joins and Bott orbifolds constructed.

Type 2 diabetes mellitus (T2DM) is a chronic disease that often results in multiple complications. Risk prediction and profiling of T2DM complications is critical for healthcare professionals to design personalized treatment plans for patients in diabetes care for improved outcomes. In this paper, we study the risk of …

Deep learning models predict postoperative complications more accurately than random forests.

Euclidean volumes of hyperbolic knots are algebraic numbers.

We describe the explicit form and the hidden structure of the answer for the HOMFLY polynomial for the figure eight and some other 3-strand knots in representation [21]. This is the first result for non-torus knots beyond (anti)symmetric representations, and its evaluation is far more complicated. We provide a whole va…

We describe a generalization of GKM theory for actions of arbitrary compact connected Lie groups. To an action satisfying the non-abelian GKM conditions we attach a graph encoding the structure of the non-abelian 1-skeleton, i.e., the subspace of points with isotopy rank at most one less than the rank of the acting gro…

We give a new algorithm for learning a two-layer neural network under a general class of input distributions. Assuming there is a ground-truth two-layer network $y = A σ(Wx) + ξ,$ where $A,W$ are weight matrices, $ξ$ represents noise, and the number of neurons in the hidden layer is no larger than the input or outp…

Develops a new method for decision trees using categorical variable structure.

Economies and societal structures in general are complex stochastic systems which may not lend themselves well to algebraic analysis. An addition of subjective value criteria to the mechanics of interacting agents will further complicate analysis. The purpose of this short study is to demonstrate capabilities of agent-…

Mathematical method based on a direct or indirect analysis of growth rates is described. It is shown how simple assumptions and a relatively easy analysis can be used to describe mathematically complicated trends and to predict growth. Only rudimentary knowledge of calculus is required. Projected trajectories based on …

We construct families of manifolds that have pairs of genus $g$ Heegaard splittings that must be stabilized roughly $g$ times to become equivalent. We also show that when two unstabilized, boundary-unstabilized Heegaard splittings are amalgamated by a "sufficiently complicated" map, the resulting splitting is unstabili…

Stratifying patients at risk for postoperative complications may facilitate timely and accurate workups and reduce the burden of adverse events on patients and the health system. Currently, a widely-used surgical risk calculator created by the American College of Surgeons, NSQIP, uses 21 preoperative covariates to asse…

Overview of structured data representation methods.

Diabetes is a major public health problem in the United States, affecting roughly 30 million people. Diabetes complications, along with the mental health comorbidities that often co-occur with them, are major drivers of high healthcare costs, poor outcomes, and reduced treatment adherence in diabetes. Here, we evaluate…

Paper addresses unbalanced data in common shock models for loss reserving.

We show that, in round spheres of dimension $n\geq3$, for any given collection of codimension 2 smooth submanifolds $\mathfrak{S}:=\{Σ_1,...,Σ_N\}$ of arbitrarily complicated topology ($N$ being the complex dimension of the spinor bundle), there is always an eigenfunction $ψ=(ψ_1,...,ψ_N)$ of the Dirac operator such th…

New method calibrates complex ODEs from noisy data using neural networks.

This is the third in a series of papers constructing hyperbolic structures on all Haken three-manifolds. This portion deals with the mixed case of the deformation space for manifolds with incompressible boundary that are not acylindrical, but are more complicated than interval bundles over surfaces. This is a slight re…

A new benchmark task for evaluating policy learning in complex, high-dimensional action spaces.

Kontsevich's formula for a deformation quantization of Poisson structures involves a Feynman series of graphs, with the weights given by some complicated integrals (using certain pullbacks of the standard angle form on a circe). We explain the geometric meaning of this series as degrees of maps of some grand configurat…

GraphVRNN generates graphs with latent variables and node attributes.

The goal of this short article is to describe the local structure of the Teichmüller stack of [8] in the neighborhood of a Kähler point. In particular we show that at a generic Kähler point X, Catanese Kur=Teich question, when interpretated at the level of stacks, has an affirmative answer. The situation may be much mo…

New models capture dynamic derivatives pricing with efficient simulations.

The theoretical existence of non-classical Schottky groups is due to Marden. Explicit examples of such kind of groups are only known in rank two, the first one by by Yamamoto in 1991 and later by Williams in 2009. In 2006, Maskit and the author provided a theoretical method to obtain examples of non-classical Schottky …

Markov networks are widely used in many Machine Learning applications including natural language processing, computer vision, and bioinformatics . Learning Markov networks have many complications ranging from intractable computations involved to the possibility of learning a model with a huge number of parameters. In t…

The goal of this paper is to describe a theoretical construction of an infinite collection of non-classical Schottky groups. We first show that there are infinitely many non-classical noded Schottky groups on the boundary of Schottky space, and we show that infinitely many of these are "sufficiently complicated". We th…

Motivated by conjectures in Heegaard Floer homology, we introduce an invariant HC(Y) of the cohomology ring of a closed 3-manifold Y whose behavior mimics that of the Heegaard Floer homology HF^\infty(Y,s) for s a torsion spin-c structure. We derive from this a numerical invariant h(Y), and obtain upper and lower bound…

Recent years have seen an increasing popularity of learning the sparse \emph{changes} in Markov Networks. Changes in the structure of Markov Networks reflect alternations of interactions between random variables under different regimes and provide insights into the underlying system. While each individual network struc…

The entropy density is an intuitive and powerful concept to study the complicated nonlinear processes derived from physical systems. We develop the minimum entropy density method (MEDM) to detect the structure scale of a given time series, which is defined as the scale in which the uncertainty is minimized, hence the p…

Important advances have been made using convolutional neural network (CNN) approaches to solve complicated problems in areas that rely on grid structured data such as image processing and object classification. Recently, research on graph convolutional neural networks (GCNN) has increased dramatically as researchers tr…

Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Predicting the occurrence of DDIs helps drug safety professionals allocate investigative resources and take appropriate regulatory action promptly. Traditional DDI prediction methods predict DDIs based on the similarity between …

Surveying joint Gaussian graphical models to identify shared structures across domains.

Abstract: Extends geometric concepts to generalized tangent bundle and describes flows.

Study on the structure of classifier boundaries in DNA sequencing.

New method trims network data to resist adversarial contamination.

Paper introduces untangling number to quantify 3-periodic tangle complexity.

The study predicts surgical complications in Crohn's disease patients using machine learning.

Let K be a fibered knot in the 3-sphere. We show that if the monodromy of K is sufficiently complicated, then Dehn surgery on K cannot yield a lens space. Work of Yi Ni shows that if K has a lens space surgery then it is fibered. Combining this with our result we see that if K has a lens space surgery then it is fibere…

Explains equivariant neural networks for machine learning.