Kernel interpolation with continuous volume sampling
Jul 12, 2020
Speakers
Ayoub Belhadji
Speaker · 0 followers
Rémi Bardenet
Speaker · 0 followers
Pierre Chainais
Speaker · 0 followers
About
A fundamental task in kernel methods is to pick nodes and weights, so as to approximate a given function from an RKHS by the weighted sum of kernel translates located at the nodes. This is the crux of kernel density estimation, kernel quadrature, or interpolation from discrete samples. Furthermore, RKHSs offer a convenient mathematical and computational framework. We introduce and analyse continuous volume sampling (VS), the continuous counterpart -for choosing node locations- of a discrete distribution introduced in (Deshpande Vempala, 2006). Our contribution is theoretical: we prove almost optimal bounds for interpolation and quadrature under VS. While similar bounds already exist for some specific RKHSs using ad-hoc node constructions, VS offers bounds that apply to any Mercer kernel and depend on the spectrum of the associated integration operator. We emphasize that, unlike previous randomized approaches that rely on regularized leverage scores or determinantal point processes, evaluating the pdf of VS only requires pointwise evaluations of the kernel. VS is thus naturally amenable to MCMC samplers.A fundamental task in kernel methods is to pick nodes and weights, so as to approximate a given function from an RKHS by the weighted sum of kernel translates located at the nodes. This is the crux of kernel density estimation, kernel quadrature, or interpolation from discrete samples. Furthermore, RKHSs offer a convenient mathematical and computational framework. We introduce and analyse continuous volume sampling (VS), the continuous counterpart -for choosing node locations- of a discrete dist…
Categories
Mathematics
Category · 2.4k presentations
AI & Data Science
Category · 10.8k presentations
Visual Arts & Graphic Design
Category · 333 presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Deep Representation earning and Clustering of Traffic Scenarios
Watch later
A new regret analysis for Adam-type algorithms
Watch later
Tightening Exploration in Upper Confidence Reinforcement Learning
Watch later
S2RMs: Spatially Structured Recurrent Modules
Watch later
Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
Watch later
Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics
Watch later
Debjani Saha, …