REVIEW 1 cited by
Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example
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
Divergence of the ADAM algorithm with fixed-stepsize: a (very) simple example
read the original abstract
A very simple unidimensional function with Lipschitz continuous gradient is constructed such that the ADAM algorithm with constant stepsize, started from the origin, diverges when applied to minimize this function in the absence of noise on the gradient. Divergence occurs irrespective of the choice of the method parameters.
Forward citations
Cited by 1 Pith paper
-
On the Convergence of Adam, Revisited
Projected Adam and listed variants have lim RT/T > 0 for all β1, β2 ∈ [0,1) on a 3-periodic linear online problem with slopes near 2, −1, −1.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.