SNAP algorithm finds approximate SOSPs for non-convex linearly constrained problems in O(1/ε^{2.5}) iterations with polynomial per-iteration complexity by leveraging strict complementarity on generic instances.
Learning the parts of objects by non-negative matrix factorization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
SNAP algorithm finds approximate SOSPs for non-convex linearly constrained problems in O(1/ε^{2.5}) iterations with polynomial per-iteration complexity by leveraging strict complementarity on generic instances.