arXiv research

Model nonstationary spatial processes using normalizing flows.

ConvNets improve nonstationary covariance estimation for large-scale spatial data.

Develops deep models to handle nonstationary spatial extremal dependence.

Flexible nonstationary Gaussian process with neural network parameters.

Spatial processes with nonstationary and anisotropic covariance structure are often used when modelling, analysing and predicting complex environmental phenomena. Such processes may often be expressed as ones that have stationary and isotropic covariance structure on a warped spatial domain. However, the warping functi…

Flexible spatial models improve predictive performance over nonstationary alternatives.

The use of covariance kernels is ubiquitous in the field of spatial statistics. Kernels allow data to be mapped into high-dimensional feature spaces and can thus extend simple linear additive methods to nonlinear methods with higher order interactions. However, until recently, there has been a strong reliance on a limi…

We derive a single pass algorithm for computing the gradient and Fisher information of Vecchia's Gaussian process loglikelihood approximation, which provides a computationally efficient means for applying the Fisher scoring algorithm for maximizing the loglikelihood. The advantages of the optimization techniques are de…

New framework models complex spatial data with basis functions and graphical vectors.

NoTMF forecasts sparse urban road movement speeds with nonstationary temporal matrix factorization.

The analysis of nonstationary time series is of great importance in many scientific fields such as physics and neuroscience. In recent years, Gaussian process regression has attracted substantial attention as a robust and powerful method for analyzing time series. In this paper, we introduce a new framework for analyzi…

A novel nonstationary permanental process relaxes kernel constraints and captures complex data patterns.

A new model predicts spatio-temporal data using adaptive decision trees and point processes.

A new method for nonstationary Gaussian processes using Fourier features.

Optimizes spectral density estimation for stationary and nonstationary processes.

Develops nonstationary MOGP kernels for better performance.

We study a special case of the problem of statistical learning without the i.i.d. assumption. Specifically, we suppose a learning method is presented with a sequence of data points, and required to make a prediction (e.g., a classification) for each one, and can then observe the loss incurred by this prediction. We go …

New method tests independence with single nonstationary time series.

Most real world phenomena such as sunlight distribution under a forest canopy, minerals concentration, stock valuation, exhibit nonstationary dynamics i.e. phenomenon variation changes depending on the locality. Nonstationary dynamics pose both theoretical and practical challenges to statistical machine learning algori…

We use diffusion models to sample from complex GP priors in climate data.

New method infers causal relationships from nonstationary time series data.

We introduce a new class of nonstationary kernels, which we derive as covariance functions of a novel family of stochastic processes we refer to as string Gaussian processes (string GPs). We construct string GPs to allow for multiple types of local patterns in the data, while ensuring a mild global regularity condition…

A new method warps inputs to learn nonstationary kernels efficiently.

Most environmental phenomena, such as wind profiles, ozone concentration and sunlight distribution under a forest canopy, exhibit nonstationary dynamics i.e. phenomenon variation change depending on the location and time of occurrence. Non-stationary dynamics pose both theoretical and practical challenges to statistica…

A new method for separating mixed signals in space and time.

Paper uses RL to estimate long-term treatment effects efficiently.

Quantum reservoir computing needs coherence influx for effective information processing.

We propose multivariate nonstationary Gaussian processes for jointly modeling multiple clinical variables, where the key parameters, length-scales, standard deviations and the correlations between the observed output, are all time dependent. We perform posterior inference via Hamiltonian Monte Carlo (HMC). We also prov…

BKTR models spatiotemporal data with scalable tensor regression.

New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.

Bayesian optimization has shown to be a fundamental global optimization algorithm in many applications: ranging from automatic machine learning, robotics, reinforcement learning, experimental design, simulations, etc. The most popular and effective Bayesian optimization relies on a surrogate model in the form of a Gaus…

It is ubiquitous in natural and social sciences that two variables, recorded temporally or spatially in a complex system, are cross-correlated and possess multifractal features. We propose a new method called multifractal detrended cross-correlation analysis (MF-DXA) to investigate the multifractal behaviors in the pow…

In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting the values of variables of interest, both of which are particularly challenging in such nonstationary environments. In this paper, we study c…

Bayesian optimization has become a fundamental global optimization algorithm in many problems where sample efficiency is of paramount importance. Recently, there has been proposed a large number of new applications in fields such as robotics, machine learning, experimental design, simulation, etc. In this paper, we foc…

A typical audio signal processing pipeline includes multiple disjoint analysis stages, including calculation of a time-frequency representation followed by spectrogram-based feature analysis. We show how time-frequency analysis and nonnegative matrix factorisation can be jointly formulated as a spectral mixture Gaussia…

FFRK automatically extracts features for spatial interpolation without external variables.

A new method optimizes in nonstationary environments with many arms efficiently.

RLGP model improves robustness and accuracy for discontinuous response surfaces.

Recent work in distance metric learning has focused on learning transformations of data that best align with provided sets of pairwise similarity and dissimilarity constraints. The learned transformations lead to improved retrieval, classification, and clustering algorithms due to the better adapted distance or similar…

Bayesian Complementary Kernelized Learning models complex spatiotemporal data.

New method disentangles latent variables in nonstationary data.

Recent work in distance metric learning has focused on learning transformations of data that best align with specified pairwise similarity and dissimilarity constraints, often supplied by a human observer. The learned transformations lead to improved retrieval, classification, and clustering algorithms due to the bette…

New kernel enables exact GP analysis of massive datasets.

Estimates neuronal connectivity from spike times using flexible Hawkes processes.

Unified formulation bridges adversarial and nonstationary bandits.

Advances in deep learning for spatio-temporal event modeling.

SA-REMBO adapts to nonstationary high-dimensional optimization.

LEAP identifies latent causal variables from temporal data.