Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors
Jul 12, 2020
Sprecher:innen
Zhaoqiang Liu
Sprecher:in · 0 Follower:innen
Selwyn Gomes
Sprecher:in · 0 Follower:innen
Avtansh Tiwari
Sprecher:in · 0 Follower:innen
Jonathan Scarlett
Sprecher:in · 0 Follower:innen
Über
The goal of standard 1-bit compressive sensing is to accurately recover an unknown sparse vector from binary-valued measurements, each indicating the sign of a linear function of the vector. Motivated by recent advances in compressive sensing with generative models, where a generative modeling assumption replaces the usual sparsity assumption, we study the problem of 1-bit compressive sensing with generative models. We first consider noiseless 1-bit measurements, and provide sample complexity bounds for approximate recovery under i.i.d. Gaussian measurements and a Lipschitz continuous generative prior, as well as a near-matching algorithm-independent lower bound. Moreover, we demonstrate that the Binary ϵ-Stable Embedding property, which characterizes the robustness of the reconstruction to measurement errors and noise, also holds for 1-bit compressive sensing with Lipschitz continuous generative models with sufficiently many Gaussian measurements. In addition, we apply our results to neural network generative models, and provide a proof-of-concept numerical experiment demonstrating significant improvements over sparsity-based approaches.The goal of standard 1-bit compressive sensing is to accurately recover an unknown sparse vector from binary-valued measurements, each indicating the sign of a linear function of the vector. Motivated by recent advances in compressive sensing with generative models, where a generative modeling assumption replaces the usual sparsity assumption, we study the problem of 1-bit compressive sensing with generative models. We first consider noiseless 1-bit measurements, and provide sample complexity b…
Kategorien
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
Mathematik
Kategorie · 2,4k Präsentationen
Über 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.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Closing the convergence gap of SGD without replacement
Später ansehen
Poster #17
Später ansehen
Invited Talk 8 Q&A
Später ansehen
Analysis of Imbalance Strategies Recommendation using a Meta-Learning Approach
Später ansehen
Deep Representation earning and Clustering of Traffic Scenarios
Später ansehen
