arXiv research

The paper introduces a frequency-domain estimator for low-order systems from noisy data.

The paper tackles system identification via Hankel nuclear norm regularization, improving estimation rates and singular value gaps.

New framework detects out-of-distribution samples efficiently.

Algorithm learns causal structures from low-order conditional independencies.

Bayesian method improves EEG source imaging accuracy by estimating skull conductivity.

New nonconvex methods improve SysID efficiency and accuracy.

This work provides a computationally efficient and statistically consistent moment-based estimator for mixtures of spherical Gaussians. Under the condition that component means are in general position, a simple spectral decomposition technique yields consistent parameter estimates from low-order observable moments, wit…

We consider the problem of computing first-passage time distributions for reaction processes modelled by master equations. We show that this generally intractable class of problems is equivalent to a sequential Bayesian inference problem for an auxiliary observation process. The solution can be approximated efficiently…

Efficient algorithm for matching graphs with community structure.

Feature selection can facilitate the learning of mixtures of discrete random variables as they arise, e.g. in crowdsourcing tasks. Intuitively, not all workers are equally reliable but, if the less reliable ones could be eliminated, then learning should be more robust. By analogy with Gaussian mixture models, we seek a…

GAMI-Tree uses model-based trees to fit low-order fANOVA models.

Optimizes mixture models without parametrizing distributions using tensor decomposition.

Principal components analysis (PCA) is the optimal linear auto-encoder of data, and it is often used to construct features. Enforcing sparsity on the principal components can promote better generalization, while improving the interpretability of the features. We study the problem of constructing optimal sparse linear a…

Paper studies statistical-computational trade-offs in tensor PCA and related problems.

Study on liquidity dynamics in Uniswap v3 pools using statistical methods.

With higher-order neighborhood information of graph network, the accuracy of graph representation learning classification can be significantly improved. However, the current higher order graph convolutional network has a large number of parameters and high computational complexity. Therefore, we propose a Hybrid Lower …

Using the classification of transitive groups we classify indecomposable quandles of size <36. This classification is available in Rig, a GAP package for computations related to racks and quandles. As an application, the list of all indecomposable quandles of size <36 not of type D is computed.

Continuous-time Bayesian networks (CTBNs) constitute a general and powerful framework for modeling continuous-time stochastic processes on networks. This makes them particularly attractive for learning the directed structures among interacting entities. However, if the available data is incomplete, one needs to simulat…

Climate projections continue to be marred by large uncertainties, which originate in processes that need to be parameterized, such as clouds, convection, and ecosystems. But rapid progress is now within reach. New computational tools and methods from data assimilation and machine learning make it possible to integrate …

We introduce and study new invariants associated with Laplace type elliptic partial differential operators on manifolds. These invariants are constructed by using the off-diagonal heat kernel; they are not pure spectral invariants, that is, they depend not only on the eigenvalues but also on the corresponding eigenfunc…

Researchers prove long-time existence for two landmark Brownian motion.

Bayesian method combines data assimilation, machine learning, and EM for chaotic dynamics.

New framework uses geometry of embeddings to predict robustness.

This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which exploits a certain tensor structure in their low-order observable moments (typically…

We develop a systematic method for classifying supersymmetric orbifold compactifications of M-theory. By restricting our attention to abelian orbifolds with low order, in the special cases where elements do not include coordinate shifts, we construct a "periodic table" of such compactifications, organized according to …

Study local equivalence of Riemannian submersions using differential invariants.

We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of predicted results when known data is represented as expansions in terms of various stochastic functions. The algorithm predicts the classif…

Hermite polynomials improve private data generation by reducing feature count.

Study how neural networks learn from non-Gaussian data models.

New framework uses score-based priors to solve ill-conditioned polynomial equations, improving signal recovery from noisy data.

New SQ lower bounds for NGCA without requiring chi-squared condition.

We propose a class of nonparametric two-sample tests with a cost linear in the sample size. Two tests are given, both based on an ensemble of distances between analytic functions representing each of the distributions. The first test uses smoothed empirical characteristic functions to represent the distributions, the s…

We introduce a notion of ternary distributive algebraic structure, give examples, and relate it to the notion of a quandle. Classification is given for low order structures of this type. Constructions of such structures from ternary bialgebras are provided. We also describe ternary distributive algebraic structures com…

Bayes-optimal limits in PCA with structured noise are determined.

We consider the inverse Ising problem, i.e. the inference of network couplings from observed spin trajectories for a model with continuous time Glauber dynamics. By introducing two sets of auxiliary latent random variables we render the likelihood into a form, which allows for simple iterative inference algorithms with…

We study a new class of codes for lossy compression with the squared-error distortion criterion, designed using the statistical framework of high-dimensional linear regression. Codewords are linear combinations of subsets of columns of a design matrix. Called a Sparse Superposition or Sparse Regression codebook, this s…

We define and study Vassiliev invariants for (long) Morse knots. It is shown that there are Vassiliev invariants which can distinguish some topologically equivalent Morse knots. In particular, there is an invariant of order 3 for Morse knots with one maximum that distinguishes two different representations of the figur…

We classify invariant Lagrangians of the form $L(g_{ij},g_{ij,k},g_{ij,kl},D_I,D_{I,j})$ depending at most quadratically on the variables $g_{ij,k},g_{ij,kl}$ and $D_I,D_{I,j}$, where $g$ is a Lorentz metric and $D$ is a tensor field of arbitrary rank on a smooth manifold. As a corollary, we prove a conjecture of Bray'…

The objective of this paper is to investigate how noisy and incomplete observations can be integrated in the process of building a reduced-order model. This problematic arises in many scientific domains where there exists a need for accurate low-order descriptions of highly-complex phenomena, which can not be directly …

A new method interprets astrophysical spectra using geometric paths to distinguish line profiles.

New fast estimation methods stemming from control theory lead to a fresh look at time series, which bears some resemblance to "technical analysis". The results are applied to a typical object of financial engineering, namely the forecast of foreign exchange rates, via a "model-free" setting, i.e., via repeated identifi…

TopoFisher learns topological summaries by maximizing Fisher information, improving parameter efficiency and inference quality.

One of the most popular approaches to understanding feature effects of modern black box machine learning models are partial dependence plots (PDP). These plots are easy to understand but only able to visualize low order dependencies. The paper is about the question 'How much can we see?': A framework is developed to qu…

The problem of topic modeling can be seen as a generalization of the clustering problem, in that it posits that observations are generated due to multiple latent factors (e.g., the words in each document are generated as a mixture of several active topics, as opposed to just one). This increased representational power …

Fast nonparametric conditional independence testing via two-stage regression

Notes on Whitney towers in 4-manifolds, focusing on local surface manipulations and invariants.

Corrected moment-based methods improve inference in topic model regression.

Develops method to construct Lie algebra weight system kernel using Vogel algebra.