NOT learns optimal transport plans, kernel costs improve performance.
problem NOT algorithm learns non-optimal plans with weak quadratic costs.
method Introduced kernel weak quadratic costs to improve NOT's performance.
result Kernel costs provide improved theoretical and practical guarantees.
Paper proposes new costs for learning multiple centers in MDNs.
problem Learning multiple centers for density approximation in MDNs.
method Combines MDNs with contrastive costs using four types of kernelized matrix costs.
result New costs improve data density approximation in MDNs.
One-shot algorithm for feature-distributed kernel PCA reduces communication costs.
problem Efficiently perform kernel PCA in distributed computing environments.
method Inspired by dual relationship between sample-distributed and feature-distributed scenarios, proposes a one-shot algorithm for feature-distributed kernel PCA.
result The algorithm provides high-quality results with low communication costs, especially when eigenvalues decay fast.
Kernel-based mean-field games use MMD penalties for interaction and target costs.
problem Optimizing mean-field games with specific cost functions.
method Kernel structure, random Fourier U-statistics, neural network training.
result Sample-level convergence theorem and rate of convergence proved.
Novel confidence intervals improve convergence rates for sparse kernel-based models.
problem High computational cost in kernel-based learning models.
method Novel confidence intervals for Nyström method and sparse variational Gaussian process approximation.
result Improved performance bounds in regression and optimization problems.
Study the cost of overfitting in noisy KRR models.
problem Cost of overfitting in noisy kernel ridge regression.
method An agnostic view of overfitting cost as a function of sample size for any target function, using Gaussian universality ansatz and task eigenstructure.
result Characterization of benign, tempered, and catastrophic overfitting.
We introduce scalable deep kernels, which combine the structural properties of deep learning architectures with the non-parametric flexibility of kernel methods. Specifically, we transform the inputs of a spectral mixture base kernel with a deep architecture, using local kernel interpolation, inducing points, and struc…
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.
A faster graph kernel using optical random features.
problem High computation cost of graphlet kernel due to isomorphism test.
method Kernel random features, optical random features, mean kernel metric.
result The proposed method is orders of magnitude faster with similar or better accuracy.
The paper analyzes the statistical cost of tuning kernel hyperparameters in robust regression.
problem Finding the best interpolant from a class of kernels with unknown hyperparameters under adversarial noise.
method Finite-sample guarantees, subsampling guarantee for linear regression, ε-net argument for discretizing kernel parameterizations.
result Hyperparameter optimization increases sample complexity by just a logarithmic factor, compared to known parameters.
Despite their success, kernel methods suffer from a massive computational cost in practice. In this paper, in lieu of commonly used kernel expansion with respect to N inputs, we develop a novel optimal design maximizing the entropy among kernel features. This procedure results in a kernel expansion with respect to en…
Kernel methods are widespread in machine learning; however, they are limited by the quadratic complexity of the construction, application, and storage of kernel matrices. Low-rank matrix approximation algorithms are widely used to address this problem and reduce the arithmetic and storage cost. However, we observed tha…
Develops kernels for matchings, overcoming computational challenges.
problem Challenges in applying kernel methods to matchings due to their discrete, non-Euclidean nature.
method Characterizes stationary kernels, introduces heat and Matérn kernel families, and develops a sub-exponential algorithm for efficient evaluation.
result Establishes novel negative results and identifies an open problem in transferring the framework to trees.
In presence of sparse noise we propose kernel regression for predicting output vectors which are smooth over a given graph. Sparse noise models the training outputs being corrupted either with missing samples or large perturbations. The presence of sparse noise is handled using appropriate use of ℓ1-norm along-wi…
Representation costs in data science: Unifying function-space views of parametric methods
problem Analyzing representation costs of parametric data-fitting methods
method Developing a general framework for analyzing representation costs through parameter-space regularizers
result Proving that many natural results hold in this abstract setting, including representer theorems for parametric methods on their native spaces
New method tunes SMC samplers efficiently without high costs.
problem Tuning SMC samplers with unadjusted kernels is challenging.
method Greedy Incremental Divergence Minimization (GIDM) for step size tuning.
result GIDM reduces KL divergence and tunes SMC samplers efficiently.
Kernel methods are an incredibly popular technique for extending linear models to non-linear problems via a mapping to an implicit, high-dimensional feature space. While kernel methods are computationally cheaper than an explicit feature mapping, they are still subject to cubic cost on the number of points. Given only …
Schrödinger bridge solved with Weyl calculus for quadratic state cost.
problem Optimal control policy to steer joint state statistics.
method Weyl calculus in quantum mechanics for reaction-diffusion PDEs.
result Explicit Markov kernel for quadratic state cost found.
BOKE optimizes expensive functions with reduced computational costs.
problem High computational cost of Gaussian process-based Bayesian optimization.
method Kernel regression and density-based exploration integrated into confidence bounds.
result BOKE achieves global convergence and superior computational efficiency.
Kernel matrices (e.g. Gram or similarity matrices) are essential for many state-of-the-art approaches to classification, clustering, and dimensionality reduction. For large datasets, the cost of forming and factoring such kernel matrices becomes intractable. To address this challenge, we introduce a new adaptive sampli…
A new method reduces Volterra kernel complexity and uncertainty quantification.
problem Challenges in modeling nonlinear systems with Volterra series due to high model order.
method Bayesian Tensor Network Volterra kernel machines (BTN-V) using canonical polyadic decomposition.
result Competitive accuracy, enhanced uncertainty quantification, and reduced computational cost.
A new distributed clustering framework using distributional kernel.
problem Clustering in distributed networks with arbitrary shapes, sizes, and densities.
method Distributed Clustering based on Distributional Kernel (KDC) using similarity of distributions.
result KDC guarantees equivalent clustering outcomes to centralized methods, reduces runtime, and discovers arbitrary clusters.
QMME balances cost and speed in convex optimization.
problem Slow convergence of first-order methods and high cost of second-order methods.
method Minimizing quadratic majorants with fixed curvature at each iteration.
result QMME framework achieves sequential convergence under standard assumptions.
Efficiently approximates kernel mean embeddings using Nyström method.
problem Computational cost of kernel mean embeddings in large-scale settings.
method Nyström method for approximating a small random subset of the dataset.
result Upper bound on approximation error with sufficient subsample size conditions.
Skyformer uses Gaussian kernel and Nyström method to speed up self-attention in transformers.
problem High computational cost of self-attention in transformers.
method Replaces softmax with Gaussian kernel and applies Nyström method for matrix approximation.
result Skyformer achieves comparable or better performance with fewer computation resources.
Gaussian processes (GPs) are flexible models that can capture complex structure in large-scale dataset due to their non-parametric nature. However, the usage of GPs in real-world application is limited due to their high computational cost at inference time. In this paper, we introduce a new framework, \textit{kernel di…
Heat kernel estimates on manifolds with mixed boundary conditions.
problem Estimating heat kernels on manifolds with ends and mixed boundary conditions.
method Global harmonic function construction and h-transform technique. result Two-sided heat kernel estimates for Riemannian manifolds with mixed boundary conditions.
Kernel methods improve geophysical forecasting accuracy and efficiency.
problem Improving geophysical forecasting models for accuracy and efficiency.
method Data-driven modeling of geophysical processes using kernel flows for faster, more accurate predictions.
result Kernel methods outperform neural networks and classical models in geophysical forecasting.
Nyström approximation for scalable operator learning
problem Scalability of operator learning for large datasets
method Nyström subsampling with operator learning
result Minimax-optimal convergence rates for functional outputs
Paper tackles non-stationary kernelized bandits with near-optimal algorithm.
problem Minimizing regret in a time-varying reward function.
method Near-optimal algorithm with a novel restarting phased elimination with random permutation (R-PERP).
result Regret upper bound matches the lower bound, making the algorithm near-optimal.
Neural processes approximate Gaussian process inference, revealing three key costs.
problem Approximating Gaussian process inference with neural processes.
method Bounding KL divergence into three components: label contamination, information bottleneck, and amortization error.
result Characterization of three costs of amortizing Gaussian process inference with neural processes.
Subsampling reduces computational cost in supervised learning in reproducing kernel Hilbert spaces.
problem Reducing computational cost in supervised learning
method Subsampling minimizes empirical risk in reproducing kernel Hilbert spaces
result Optimal subsampling scheme revealed
LUNA improves linear attention for long sequences without sacrificing accuracy.
problem Quadratic computational cost of softmax attention in long-sequence domains.
method LUNA learns a learnable kernel feature map to reduce attention cost to linear while maintaining accuracy.
result LUNA achieves state-of-the-art performance on the LRA and excels at post-hoc conversion.
Efficient tensor kernel method reduces memory usage and computational cost for sparse regression.
problem Memory and computational limitations in tensor kernel methods for sparse regression.
method Proposes a new tensor data layout and Nystrom subsampling approach to reduce memory and computational requirements.
result Improvements lead to more efficient tensor kernel methods for sparse regression.
New kernels capture both local and non-local interactions efficiently.
problem Designing kernels that capture both local and non-local interactions while remaining computationally tractable.
method Spectral truncation kernels based on C∗-algebra. result Spectral truncation kernels induce interactions across the data function domain and reduce computational cost.
A new method speeds up computation of Sinkhorn divergences to linear time.
problem Expensive computation of Sinkhorn divergences for comparing probability distributions.
method Using positive features to approximate ground costs, reducing computation time to linear.
result Sinkhorn divergences can be computed in linear time, scaling as O(nr).
The computational complexity of kernel methods has often been a major barrier for applying them to large-scale learning problems. We argue that this barrier can be effectively overcome. In particular, we develop methods to scale up kernel models to successfully tackle large-scale learning problems that are so far only …
We consider the problem of simultaneously learning to linearly combine a very large number of kernels and learn a good predictor based on the learnt kernel. When the number of kernels d to be combined is very large, multiple kernel learning methods whose computational cost scales linearly in d are intractable. We p…
We solve a Schrödinger bridge with a quadratic state cost, finding a closed-form solution.
problem Optimizing diffusion processes between given distributions.
method Regularized Schrödinger bridge with a quadratic state cost.
result Closed-form solution for the Markov kernel of the regularized Schrödinger bridge.
We introduce a new structured kernel interpolation (SKI) framework, which generalises and unifies inducing point methods for scalable Gaussian processes (GPs). SKI methods produce kernel approximations for fast computations through kernel interpolation. The SKI framework clarifies how the quality of an inducing point a…
A new method estimates generative model mappings using kernel transfer operators, reducing costs and improving performance.
problem Efficiently estimating mappings between known and unknown distributions in generative models.
method Adapting kernel transfer operators to estimate mappings, reducing computational costs.
result Significant runtime savings and good empirical performance compared to existing methods.
Graph-based methods pervade the inference toolkits of numerous disciplines including sociology, biology, neuroscience, physics, chemistry, and engineering. A challenging problem encountered in this context pertains to determining the attributes of a set of vertices given those of another subset at possibly different ti…
In most adaptive signal processing applications, system linearity is assumed and adaptive linear filters are thus used. The traditional class of supervised adaptive filters rely on error-correction learning for their adaptive capability. The kernel method is a powerful nonparametric modeling tool for pattern analysis a…
At initialization, artificial neural networks (ANNs) are equivalent to Gaussian processes in the infinite-width limit, thus connecting them to kernel methods. We prove that the evolution of an ANN during training can also be described by a kernel: during gradient descent on the parameters of an ANN, the network functio…
Kernel methods form a theoretically-grounded, powerful and versatile framework to solve nonlinear problems in signal processing and machine learning. The standard approach relies on the \emph{kernel trick} to perform pairwise evaluations of a kernel function, leading to scalability issues for large datasets due to its …
The paper examines how kernel approximations affect Gaussian process regression in large data applications.
problem Effect of kernel approximations on Gaussian process regression in large data applications.
method Unified framework to analyze Gaussian process regression under computational and epistemic misspecification.
result Theoretical analysis of Gaussian process regression under various misspecifications.
New DCD and BDCD methods for K-SVM and K-RR reduce communication costs.
problem Scalability issues in DCD and BDCD methods for kernel problems.
method Developed scalable s-step variants of DCD and BDCD methods. result Achieved strong scaling speedups of up to 9.8x over existing methods.
New method reduces computational cost for learning stationary diffusions.
problem Learning parameters of stationary diffusions efficiently.
method Stein-type discrepancy (SKDS) for estimating generator expectations.
result SKDS guarantees alignment with target stationary distribution.