arXiv research

Markov networks (MNs) are a powerful way to compactly represent a joint probability distribution, but most MN structure learning methods are very slow, due to the high cost of evaluating candidates structures. Dependency networks (DNs) represent a probability distribution as a set of conditional probability distributio…

Many applications infer the structure of a probabilistic graphical model from data to elucidate the relationships between variables. But how can we train graphical models on a massive data set? In this paper, we show how to construct coresets -compressed data sets which can be used as proxy for the original data and ha…

Batch normalization improves deep networks by aligning their decision boundaries with data.

We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of max-affine spline operators (MASOs), which provide a powerful portal through which to view and analyze their inner workings. …

We study the geometry of deep (neural) networks (DNs) with piecewise affine and convex nonlinearities. The layers of such DNs have been shown to be {\em max-affine spline operators} (MASOs) that partition their input space and apply a region-dependent affine mapping to their input to produce their output. We demonstrat…

Paper improves DNS typo-squatting detection with ensemble model.

Stream deinterleaving is an important problem with various applications in the cybersecurity domain. In this paper, we consider the specific problem of deinterleaving DNS data streams using machine-learning techniques, with the objective of automating the extraction of malware domain sequences. We first develop a gener…

DN estimator mitigates network interference in experiments.

Paper proves DN map determination for simple surfaces with low regularity metrics.

Given a geodesic space (E, d), we show that full ordinal knowledge on the metric d-i.e. knowledge of the function D d : (w, x, y, z) $\rightarrow$ 1 d(w,x)$\le$d(y,z) , determines uniquely-up to a constant factor-the metric d. For a subspace En of n points of E, converging in Hausdorff distance to E, we construct a met…

Reconstructing a planar domain from its Dirichlet-to-Neumann data

Nonlinearity is crucial to the performance of a deep (neural) network (DN). To date there has been little progress understanding the menagerie of available nonlinearities, but recently progress has been made on understanding the rôle played by piecewise affine and convex nonlinearities like the ReLU and absolute value …

In a recent paper, Belishev and Sharafutdinov consider a compact Riemannian manifold $M$ with boundary $\partial M$. They define a generalized Dirichlet to Neumann (DN) operator $Λ$ on all forms on the boundary and they prove that the real additive de Rham cohomology structure of the manifold in question is completely …

DeepTensor uses deep networks to efficiently decompose tensors with improved performance and robustness.

Physics-informed model reduces RBC simulation costs.

We consider the problem of identifying a unitary Yang-Mills connection $\nabla$ on a Hermitian vector bundle from the Dirichlet-to-Neumann (DN) map of the connection Laplacian $\nabla^*\nabla$ over compact Riemannian manifolds with boundary. We establish uniqueness of the connection up to a gauge equivalence in the cas…

TURB-Rot provides a large database of turbulent rotating flow snapshots for research.

We study Hölder continuity of solutions to the Monge-Ampère equations on compact Kähler manifolds. In [DNS] the authors have shown that the measure $ω_u^n$ is moderate if $u$ is Hölder continuous. We prove a theorem which is a partial converse to this result.

Let M be a compact, connected surface, possibly with a finite set of points removed from its interior. Let d,n be positive integers, and let N be a d-fold covering space of M. We show that the covering map induces an embedding of the n-th braid group B_n(M) of M in the (dn)-th braid group B_{dn}(N) of N, and give sever…

Study assesses data-driven and physics-based SGS models for transcritical combustion.

Physics-informed neural networks improve surrogate modeling of turbulent Rayleigh-Bénard convection.

We analyze low rank tensor completion (TC) using noisy measurements of a subset of the tensor. Assuming a rank-$r$, order-$d$, $N \times N \times \cdots \times N$ tensor where $r=O(1)$, the best sampling complexity that was achieved is $O(N^{\frac{d}{2}})$, which is obtained by solving a tensor nuclear-norm minimizatio…

New framework uses conformal predictions for robust, scalable machine learning classification.

$\newcommand{\ball}{\mathbb{B}}\newcommand{\dsQ}{\mathcal{Q}}\newcommand{\dsS}{\mathcal{S}}$In this work we study a fair variant of the near neighbor problem. Namely, given a set of $n$ points $P$ and a parameter $r$, the goal is to preprocess the points, such that given a query point $q$, any point in the $r$-neighbor…

A new method improves graph node embeddings by considering both nearby and distant node similarities.

Spatio-temporal data are ubiquitous in the agricultural, ecological, and environmental sciences, and their study is important for understanding and predicting a wide variety of processes. One of the difficulties with modeling spatial processes that change in time is the complexity of the dependence structures that must…

Study inverse boundary value problem for Monge-Ampère equation on convex domains.

A distributed algorithm reduces communication cost in linear bandits to near-optimal levels.

Machine learning models outperform traditional econometric methods for forecasting term structure of government bonds

Neural network predicts turbulence near-wall regions efficiently.

The discrete Nahm equations, a system of matrix valued difference equations, arose in the work of Braam and Austin on half-integral mass hyperbolic monopoles. We show that the discrete Nahm equations are completely integrable in a natural sense: to any solution we can associate a spectral curve and a holomorphic line-b…

The paper solves the Steklov spectral inverse problem for conformal metrics.

The study finds the number of closed geodesics on a specific type of manifold.

Paper optimizes GAIL for online and offline learning with linear approximations.

Convolutional networks predict turbulence from wall quantities.

This paper presents a novel method to compute the exact Kantorovich-Wasserstein distance between a pair of $d$-dimensional histograms having $n$ bins each. We prove that this problem is equivalent to an uncapacitated minimum cost flow problem on a $(d+1)$-partite graph with $(d+1)n$ nodes and $dn^{\frac{d+1}{d}}$ arcs,…

Explicit relation found between knot torsion and TQFT signatures.

New neural network class approximates Hölder functions with optimal error and sample complexity.

Rank regression from pairwise comparisons requires many comparisons to accurately learn model parameters.

To a complex projective structure $Σ$ on a surface, Thurston associates a locally convex pleated surface. We derive bounds on the geometry of both in terms of the norms $\|φ_Σ\|_\infty$ and $\|φ_Σ\|_2$ of the quadratic differential $φ_Σ$ of $Σ$ given by the Schwarzian derivative of the associated locally univalent map.…

Quaternion Conformer GAN (QC-GAN) is a parameter-efficient speech enhancement framework that combines a Quaternion Conformer generator with MetricGAN-based training.

In this paper we consider the problem of identifying a connection $\nabla$ on a vector bundle up to gauge equivalence from the Dirichlet-to-Neumann map of the connection Laplacian $\nabla^*\nabla$ over conformally transversally anisotropic (CTA) manifolds. This was proved in \cite{LCW} for line bundles in the case of t…

Paper improves convergence rate of Langevin Dynamics algorithms.

The paper provides bounds for high-dimensional U-statistics with novel order-explicit inequalities.

Extremes play a special role in Anomaly Detection. Beyond inference and simulation purposes, probabilistic tools borrowed from Extreme Value Theory (EVT), such as the angular measure, can also be used to design novel statistical learning methods for Anomaly Detection/ranking. This paper proposes a new algorithm based o…

This paper proposes a generic classification system designed to detect security threats based on the behavior of malware samples. The system relies on statistical features computed from proxy log fields to train detectors using a database of malware samples. The behavior detectors serve as basic reusable building block…

A fully-convolutional neural-network model is used to predict the streamwise velocity fields at several wall-normal locations by taking as input the streamwise and spanwise wall-shear-stress planes in a turbulent open channel flow. The training data are generated by performing a direct numerical simulation (DNS) at a f…

In this paper we introduce a novel framework for making exact nonparametric Bayesian inference on latent functions, that is particularly suitable for Big Data tasks. Firstly, we introduce a class of stochastic processes we refer to as string Gaussian processes (string GPs), which are not to be mistaken for Gaussian pro…