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...
Príomhchruthaitheoirí: | Sarao Mannelli, S, Biroli, G, Cammarota, C, Krzakala, F, Urbani, P, Zdeborová, L |
---|---|
Formáid: | Journal article |
Teanga: | English |
Foilsithe / Cruthaithe: |
American Physical Society
2020
|
Míreanna comhchosúla
-
Marvels and Pitfalls of the Langevin Algorithm in Noisy High-Dimensional Inference
de réir: Stefano Sarao Mannelli, et al.
Foilsithe / Cruthaithe: (2020-03-01) -
Thresholds of descending algorithms in inference problems
de réir: Sarao Mannelli, S, et al.
Foilsithe / Cruthaithe: (2020) -
The Noisy and Marvelous Molecular World of Biology
de réir: Felix Ritort
Foilsithe / Cruthaithe: (2019-04-01) -
Theoretical characterization of uncertainty in high-dimensional linear classification
de réir: Lucas Clarté, et al.
Foilsithe / Cruthaithe: (2023-01-01) -
Glassy Nature of the Hard Phase in Inference Problems
de réir: Fabrizio Antenucci, et al.
Foilsithe / Cruthaithe: (2019-01-01)