This work explores variably scaled kernels to improve non-stationary Gaussian processes.
problem Limited ability of stationary kernels to represent heterogeneous correlation structures.
method Introduces variably scaled kernels to modify correlation structures explicitly.
result Improved reconstruction accuracy and better uncertainty estimates for non-stationary data.
We propose a new method for input variable selection in nonlinear regression. The method is embedded into a kernel regression machine that can model general nonlinear functions, not being a priori limited to additive models. This is the first kernel-based variable selection method applicable to large datasets. It sides…
Improves kernel ridge regression by optimizing scale and feature parameters.
problem Kernel ridge regression with fixed kernel.
method Introduces a matrix parameter U to optimize scale and feature parameters.
result Solves a nonlinear variational problem to optimize U.
Kernel improves Gaussian process scalability for wide datasets.
problem Under-performance of Gaussian processes on wide data.
method Introduces Bézier Gaussian Process kernel with exponential summarising variables growth and linear cost.
result Empirically demonstrates scalability to both tall and wide datasets.
RFFNet scales kernel methods to large datasets by learning kernel relevance.
problem Scaling kernel methods to large datasets while maintaining interpretability.
method Designs random Fourier features for ARD kernels and uses first-order stochastic optimization for learning kernel relevances.
result RFFNet achieves low prediction error and identifies relevant features, leading to more interpretable solutions.
Study on kernel methods in large-scale machine learning problems.
problem Large-scale machine learning with many interacting variables.
method Mean field limit analysis of kernels and their Hilbert spaces.
result Mean field convergence of empirical and infinite-sample solutions.
This paper presents a variational Bayesian kernel selection (VBKS) algorithm for sparse Gaussian process regression (SGPR) models. In contrast to existing GP kernel selection algorithms that aim to select only one kernel with the highest model evidence, our proposed VBKS algorithm considers the kernel as a random varia…
In this paper, we propose an outlier-robust regularized kernel-based method for linear system identification. The unknown impulse response is modeled as a zero-mean Gaussian process whose covariance (kernel) is given by the recently proposed stable spline kernel, which encodes information on regularity and exponential …
Deep neural networks learn by averaging fast variables, revealing a Gaussian process.
problem Analyzing the complex behavior of deep neural networks (DNNs) with billions of parameters.
method Identifying slow variables that average the erratic behavior of fast microscopic variables in fully trained DNNs.
result DNN layers couple only through the second moment (kernels) of their activations and pre-activations, which fluctuate in a nearly Gaussian manner.
Despite the success of the popular kernelized support vector machines, they have two major limitations: they are restricted to Positive Semi-Definite (PSD) kernels, and their training complexity scales at least quadratically with the size of the data. Many natural measures of similarity between pairs of samples are not…
This paper focuses on Bayesian Optimization (BO) for objectives on combinatorial search spaces, including ordinal and categorical variables. Despite the abundance of potential applications of Combinatorial BO, including chipset configuration search and neural architecture search, only a handful of methods have been pro…
Kernel analog forecasting studied for multiscale systems.
problem Interpreting data-driven predictions in multiscale dynamical systems.
method Kernel analog forecasting methods applied to multiscale systems with varying Markovian closures.
result Guidance provided for interpreting data-driven predictions in practice.
MOCK learns complex systems from trajectories efficiently.
problem Learning nonparametric differential equations from high-dimensional data.
method MOCK uses multivariate occupation kernel functions to learn vector fields linearly.
result MOCK outperforms other methods on various datasets.
Bayesian Complementary Kernelized Learning models complex spatiotemporal data.
problem Modeling complex, nonstationary, and nonseparable spatiotemporal data.
method Integrates kernelized low-rank tensor factorization and short-range spatiotemporal Gaussian Processes.
result BCKL offers superior performance in providing accurate posterior mean and high-quality uncertainty estimates.
WE constructs GP kernels for mixed inputs using weighted EDMs.
problem Limitation of standard GP models in handling categorical variables.
method WEGP constructs kernel function using weighted EDMs for categorical inputs.
result WEGP improves GP model accuracy in both synthetic and real-world optimization problems.
Study on infinitely-wide CNNs and their adaptability to function spatial scales.
problem Understanding how CNNs efficiently learn high-dimensional functions and their adaptability to function spatial scales.
method Study infinitely-wide deep CNNs in the kernel regime, characterizing their spectrum and using generalisation bounds to prove adaptability.
result Deep CNNs adapt to the spatial scale of the target function, with error decay controlled by the effective dimensionality of function subsets.
Multi-output Gaussian processes (MOGPs) are an extension of Gaussian Processes (GPs) for predicting multiple output variables (also called channels, tasks) simultaneously. In this paper we use the convolution theorem to design a new kernel for MOGPs, by modeling cross channel dependencies through cross convolution of t…
New method speeds up HSIC for multiple variables.
problem Quadratic computational complexity of HSIC for multiple variables.
method Nyström approximation to HSIC for M≥2. result Consistent Nyström HSIC estimator for M≥2. Framework achieves fairness in predictions using partially known causal graph over clusters of variables.
problem Achieving fairness in algorithmic decisions when causal graph knowledge is limited.
method Leverages a causal graph over clusters of variables to train a prediction model, reducing interventional distribution discrepancies.
result Framework strikes a better balance between fairness and accuracy than existing approaches under limited causal graph knowledge.
In this paper, we propose a variable selection method for general nonparametric kernel-based estimation. The proposed method consists of two-stage estimation: (1) construct a consistent estimator of the target function, (2) approximate the estimator using a few variables by l1-type penalized estimation. We see that the…
Large scale online kernel learning aims to build an efficient and scalable kernel-based predictive model incrementally from a sequence of potentially infinite data points. A current key approach focuses on ways to produce an approximate finite-dimensional feature map, assuming that the kernel used has a feature map wit…
Proposes a method to select variables for kernel two-sample tests.
problem Determining whether two samples have the same distribution using informative variables.
method A framework based on kernel maximum mean discrepancy (MMD) for selecting a subset of variables.
result The sample size requirements for the three kernels depend on the number of selected variables, not the data dimension.
We show that, when considering the anisotropic scaling factors and their derivatives as affine variables, the coefficients of the heat kernel expansion of the Dirac-Laplacian on SU(2) Bianchi IX metrics are algebro-geometric periods of motives of complements in affine spaces of unions of quadrics and hyperplanes. We …
New kernel model scales to large datasets.
problem Challenges in scaling kernel machines to large datasets.
method Introduced EigenPro 3.0, an algorithm based on projected dual preconditioned SGD.
result Ability to scale model and data sizes independently.
Improves Bayesian optimization efficiency for mixed variable spaces.
problem Boosting sample efficiency in Bayesian optimization for mixed variable spaces.
method Proposes frequency modulated (FM) kernels to model complex dependencies across different types of variables.
result BO-FM outperforms competitors in various optimization problems.
This work bridges two views of feature learning in neural networks.
problem The relationship between kernel scale changes and data-adaptive feature learning in neural networks remains unresolved.
method Using statistical mechanics, the work derives analytical expressions for network output statistics across scaling regimes.
result Kernel adaptation can be reduced to an effective kernel rescaling, but multi-scale adaptive approach provides richer insights.
The article proposes modified Gower's coefficients for handling mixed type variables in nearest neighbor methods.
problem Handling mixed type variables in nearest neighbor methods, especially imputation and statistical matching.
method Suggests modifications to the Gower's distance for interval and ratio scaled variables to address unbalanced contributions and outlier sensitivity.
result Improved distance calculations reduce the unbalanced contribution of different variable types and attenuate outlier effects.
Model shows feature learning can improve neural scaling laws for hard tasks.
problem Understanding and improving neural network scaling laws for various task difficulties.
method Developed a solvable model of neural scaling laws, identified three scaling regimes, and demonstrated feature learning's impact on scaling exponents.
result Feature learning can improve scaling with training time and compute for hard tasks, nearly doubling the exponent.
We improve kernel ridge regression for skewed responses using oversampling and adaptive partitioning.
problem Kernel ridge regression struggles with skewed response variables, leading to poor estimates.
method Combines adaptive partitioning with oversampling to address skewed responses in kernel ridge regression.
result The proposed method yields estimates with smaller risk compared to classical methods under mild conditions.
SigGPDE scales sparse Gaussian processes for sequential data.
problem Predicting and quantifying uncertainty in sequential data.
method Sparse variational inference framework for Gaussian Processes, leveraging GP signature kernel gradients as PDE solutions.
result Significant computational gains and state-of-the-art performance on large sequential datasets.
Accurate approximations to density functionals have recently been obtained via machine learning (ML). By applying ML to a simple function of one variable without any random sampling, we extract the qualitative dependence of errors on hyperparameters. We find universal features of the behavior in extreme limits, includi…
Optimal kernel learning improves GP regression for high-dimensional inputs.
problem High computational costs and low prediction accuracy in GP models with many inputs.
method Approximates GP covariance with a convex combination of kernel functions, identifying active variables.
result Improves prediction accuracy and correctly identifies active input variables.
Paper presents a spatio-temporal Bayesian model for early detection of COVID-19 hotspots.
problem Understanding spatio-temporal dynamics of COVID-19 hotspots to prevent outbreaks.
method Spatio-temporal Bayesian framework with a zero-mean Gaussian process and non-stationary kernel function enhanced by deep neural networks.
result Model demonstrates superior hotspot-detection performance compared to baseline methods.
New MCMC method speeds up quantum physics simulations by a factor of 100.
problem Simulating quantum many-body systems with high computational complexity.
method FFT-accelerated MCMC with coupled particle and auxiliary variables.
result Achieves O(NlogN) scaling, significantly faster than traditional O(N3) methods. FastKCI speeds up KCI tests for causal inference on large datasets.
problem Cubic computational complexity of kernel-based conditional independence tests.
method Mixture-of-experts approach with parallel Gaussian process inference.
result Substantial computational speedups with maintained statistical power.
Nonlinear kernel regression models are often used in statistics and machine learning because they are more accurate than linear models. Variable selection for kernel regression models is a challenge partly because, unlike the linear regression setting, there is no clear concept of an effect size for regression coeffici…
Researchers parallelize neural kernels for large-scale data, achieving state-of-the-art accuracy.
problem Limited scalability of neural kernels on large datasets.
method Massively parallel computation across many GPUs, combined with a distributed, preconditioned conjugate gradients algorithm.
result Achieved state-of-the-art accuracy of 91.2% on CIFAR-5m dataset using neural kernels.
Existing multi-view learning methods based on kernel function either require the user to select and tune a single predefined kernel or have to compute and store many Gram matrices to perform multiple kernel learning. Apart from the huge consumption of manpower, computation and memory resources, most of these models see…
Efficiently scales continuous kernels with sparse Fourier domain learning.
problem High computational and memory demands, spectral bias in continuous kernels.
method Sparse learning in the Fourier domain.
result Efficient scaling of continuous kernels, reduced computational and memory requirements, mitigated spectral bias.
The paper analyzes learning curves for kernel ridge regression with dot-product kernels.
problem Understanding the learning curves for different scaling regimes of data and model.
method Precise formulas for mean test error, bias, and variance in the mo∞ with m/dr constant regime. result A peak in the learning curve at m≈dr/r! for any integer r. Criterion extends identifiability for continuous mixtures of kernels.
problem Identify continuous mixtures of kernels.
method Generating-function accessibility criterion based on moment-generating functions or Laplace transforms.
result Criterion applies to mixtures of discrete and continuous variables.
Kernel method improves instrumental variable regression rates.
problem Nonparametric instrumental variable regression with weak instruments.
method Kernel-based two-stage least-squares method, strong L2 convergence analysis. result Minimax optimal rates for instrumental regression under standard assumptions.
A new, fast kernel test for large data.
problem Efficient kernel two-sample tests for high-dimensional, large-scale data.
method A new kernel-based test that is computationally efficient and robust to high dimensions.
result The new test performs well across various alternatives and dimensions.
Kernel embeddings help estimate causal effects from observational data.
problem Estimating causal effects from observational data with confounding variables.
method Kernel embeddings in reproducing kernel Hilbert spaces (RKHS).
result Robust nonparametric framework for causal inference.
Kernel methods are powerful and flexible approach to solve many problems in machine learning. Due to the pairwise evaluations in kernel methods, the complexity of kernel computation grows as the data size increases; thus the applicability of kernel methods is limited for large scale datasets. Random Fourier Features (R…
Efficiently applies NTK to large-scale datasets using random features.
problem Computational limitations of kernel methods for large-scale datasets.
method Proposes a sketching-based algorithm combining random features of arc-cosine kernels to construct an efficient feature map of the NTK.
result Achieves comparable error bounds to exact kernel methods but with significantly reduced feature dimensionality.
Proposes an online method for high-dimensional streaming data.
problem Increasing variable dimensions with sample size in online kernel sliced inverse regression.
method Introduces approximate linear dependence condition and dictionary variable sets to address the problem. Transforms into online generalized eigen-decomposition problem and uses stochastic optimization for updates.
result Achieves close performance to batch processing kernel sliced inverse regression.
Derives a family of hyperparameter scaling strategies for neural networks.
problem Optimizing hyperparameters for wide and deep neural networks.
method Introduces a one-parameter family of hyperparameter scaling strategies.
result Reveals proper scaling of depth with width for large-scale models.