REVIEW 2 cited by
Active manifolds, stratifications, and convergence to local minima in nonsmooth optimization
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
read the original abstract
We show that the subgradient method converges only to local minimizers when applied to generic Lipschitz continuous and subdifferentially regular functions that are definable in an o-minimal structure. At a high level, the argument we present is appealingly transparent: we interpret the nonsmooth dynamics as an approximate Riemannian gradient method on a certain distinguished submanifold that captures the nonsmooth activity of the function. In the process, we develop new regularity conditions in nonsmooth analysis that parallel the stratification conditions of Whitney, Kuo, and Verdier and extend stochastic processes techniques of Pemantle.
Forward citations
Cited by 2 Pith papers
-
On exploration of an interior mirror descent flow for stochastic nonconvex constrained problem
A Riemannian subgradient differential inclusion unifies Hessian barrier and mirror descent methods and explains their spurious stationary points as stable equilibria outside the true stationary set.
-
Stability of first-order methods in tame optimization
For locally Lipschitz tame functions, stable points of first-order methods are exactly local minima, strict local minima are stable, and the critical-point set is globally stable for coercive functions.
Discussion (0). Continue with ORCID to comment.