Work

Marvels and Pitfalls of the Langevin Algorithm in Noisy High-Dimensional Inference

Year: 2020

Type: article

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.

Source: Physical Review X

DOI: 10.1103/physrevx.10.011057

Authors: Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová

Institutions: Centre National de la Recherche Scientifique, Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Université Paris-Saclay, Institut de Physique Théorique, Université Paris Sciences et Lettres, École Normale Supérieure - PSL, Sorbonne Université, Laboratoire de Physique de l'Ecole Normale Supérieure, Université Paris Diderot, King's College London, Université Pierre-et-Marie-Curie

Language: English

Topic: Markov Chains and Monte Carlo Methods

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,849

Funders: Simons Foundation, Agence Nationale de la Recherche, Laboratoire d’excellence Physique Atomes Lumière Matière, Invention for Innovation Programme, H2020 European Research Council, H2020 Marie Skłodowska-Curie Actions

Awards: G1706765028, Physics: Atoms, Light, Matter, G3117488297, G392606314, G457735187, G5452052347, Combinatorial Structures and Processes, G7917003928

OpenAlex ID: W3008596124

FWCI: 6.178

Cites: 93

Cited by: 59

Related to: 10