Marvels and pitfalls of the Langevin algorithm in noisy high-dimensional inference
Gradient-descent-based algorithms and their stochastic versions have widespread applications in machine learning and statistical inference. In this work, we carry out an analytic study of the performance of the algorithm most commonly considered in physics, the Langevin algorithm, in the context of...
主要な著者: | Sarao Mannelli, S, Biroli, G, Cammarota, C, Krzakala, F, Urbani, P, Zdeborová, L |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
American Physical Society
2020
|
類似資料
-
Marvels and Pitfalls of the Langevin Algorithm in Noisy High-Dimensional Inference
著者:: Stefano Sarao Mannelli, 等
出版事項: (2020-03-01) -
Thresholds of descending algorithms in inference problems
著者:: Sarao Mannelli, S, 等
出版事項: (2020) -
The Noisy and Marvelous Molecular World of Biology
著者:: Felix Ritort
出版事項: (2019-04-01) -
Theoretical characterization of uncertainty in high-dimensional linear classification
著者:: Lucas Clarté, 等
出版事項: (2023-01-01) -
Glassy Nature of the Hard Phase in Inference Problems
著者:: Fabrizio Antenucci, 等
出版事項: (2019-01-01)