REVIEW
High-Dimensional Non-Convex Landscapes and Gradient Descent Dynamics
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
classification
cond-mat.dis-nncond-mat.stat-mech
keywords
dynamicshigh-dimensionalphysicsdescentdevelopedgradientlandscapesnon-convex
Signed reviews
read the original abstract
In these lecture notes we present different methods and concepts developed in statistical physics to analyze gradient descent dynamics in high-dimensional non-convex landscapes. Our aim is to show how approaches developed in physics, mainly statistical physics of disordered systems, can be used to tackle open questions on high-dimensional dynamics in Machine Learning.
Discussion (0). Continue with ORCID to comment.