Marvels and Pitfalls of the Langevin Algorithm in Noisy High-Dimensional Inference
Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
Abstract
A tool for benchmarking one of the algorithms most commonly used in machine-learning provides insight into its performance and could lead to a better theoretical understanding of how similar algorithms work.
Topics & Concepts
AlgorithmComputer scienceBenchmarkingInferenceNoise (video)Langevin dynamicsNoisy dataSignal processingArtificial intelligenceStatistical inferenceBenchmark (surveying)Optimization algorithmSelection (genetic algorithm)Blind Source Separation TechniquesSparse and Compressive Sensing TechniquesBayesian Methods and Mixture Models