paper-with-me

Papers

Variance-Reducing Couplings for Random Features

2024-05-26 · Isaac Reid, Stratis Markou, Krzysztof Choromanski, Richard E. Turner, Adrian Weller

Random features (RFs) are a popular technique to scale up kernel methods in machine learning, replacing exact kernel evaluations with stochastic Monte Carlo estimates. They underpin models as diverse as efficient transformers (by approximating attention) to sparse spectrum Gaussian processes (by approximating the covariance function). Efficiency can be further improved by speeding up the convergence of these estimates: a variance reduction problem. We tackle this through the unifying lens of optimal transport, finding couplings to improve RFs defined on both Euclidean and discrete input spaces. They enjoy theoretical guarantees and sometimes provide strong downstream gains, including for scalable approximate inference on graphs. We reach surprising conclusions about the benefits and limitations of variance reduction as a paradigm, showing that other properties of the coupling should be optimised for attention estimation in efficient transformers.

📄 PDF Abstract BibTeX arXiv:2405.16541

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian Processes

Similar Papers 제목 키워드 기반

Dimension of activity in random neural networks

2022-07-25 · David G. Clark, L. F. Abbott, Ashok Litwin-Kumar

Neural networks are high-dimensional nonlinear dynamical systems that process information through the coordinated activity of many connected units. Understanding how biological and machine-learning networks function and …

Covariance Shrinkage via Stochastic Interpolation

2026-06-05 · Mathieu Chalvidal, Florentin Coeurdoux, Eric Vanden-Eijnden arxiv

We recast classical shrinkage of high-dimensional covariance estimators as empirical risk minimization over a parametric stochastic interpolant between a source and a target distribution. This formalism recovers known sh…

A Mutually-Dependent Hadamard Kernel for Modelling Latent Variable Couplings

2017-02-27 · Sami Remes, Markus Heinonen, Samuel Kaski

We introduce a novel kernel that models input-dependent couplings across multiple latent processes. The pairwise joint kernel measures covariance along inputs and across different latent signals in a mutually-dependent f…

Bayesian InferenceClassificationEEGElectroencephalogram (EEG)+1

Barycentric Projections of Optimal Transport Plans on Riemannian Manifolds

2026-06-06 · Kisung You arxiv

Optimal transport couplings are probabilistic objects, while many learning pipelines require deterministic maps. In Euclidean space, barycentric projection converts a coupling into a map by taking conditional expectation…

A statistical physics approach to learning curves for the Inverse Ising problem

2017-05-15 · Ludovica Bachschmid-Romano, Manfred Opper

Using methods of statistical physics, we analyse the error of learning couplings in large Ising models from independent data (the inverse Ising problem). We concentrate on learning based on local cost functions, such as …