Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features
Jul 12, 2020
Speakers
Liang Ding
Speaker · 1 follower
Shahin Shahrampour
Speaker · 0 followers
About
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 entropic optimal features (EOF), improving the data representation dramatically due to features dissimilarity. Under mild technical assumptions, our generalization bound shows that with only O(N^1/4) features (disregarding logarithmic factors), we can achieve the optimal statistical accuracy (i.e., O(1/√(N))). The salient feature of our design is its sparsity that significantly reduces the time and space cost. Our numerical experiments on benchmark datasets verify the superiority of EOF over the state-of-the-art in kernel approximation.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 entropic optimal features (EOF), improving the data representation dramatically due to features dissimilarity. Under mild technical assumptions, our generalization bound shows that wit…
Categories
App & Game Development
Category · 954 presentations
AI & Data Science
Category · 10.8k 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
Graph Neural Networks in TensorFlow and Keras with Spektral
Watch later
Sets Clustering
Watch later
Recurrent Convolutional Network based Hybrid Video Compression
Watch later
Word-Level Speech Recognition With a Letter to Word Encoder
Watch later
When Explanations Lie: Why Many Modified BP Attributions Fail
Watch later
Leon Sixt, …
What an agent knows: evaluation in open worlds
Watch later
Alex Kearney, …