Multi Step Anchored Cohypomonotone — Cohypomonotone Operator Inclusions
Descriptions may be stale. Consult the linked Lean sources.
Cohypomonotone Operator Inclusions · Lean proof
Cohypomonotone Operator Inclusions
We seek a zero of
The inclusion problem is to find
Our assumptions:
Assumption 1 (Lipschitz continuity and
monotonicity). For every
Assumption 2 (Cohypomonotonicity). For every
Assumption 3 (Resolvent access). There is a map
Assumption 4 (Initial distance). There exists
After the allotted oracle calls, the output must satisfy
Proved result
OracleTemplate.Convergence LongTails.Setups.CohypomonotoneInclusion.spec OracleTemplate.CohypomonotoneInclusion.budgetRelevant previous results
- Yang Cai, Argyris Oikonomou, Weiqiang Zheng. Accelerated Algorithms for
Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone
Inclusion. 2022 preprint (v2); published at ICML 2024. Complexity:
exact operator evaluations and monotone-operator resolvent calls, including initialization, for the accelerated splitting method (composite-FEG), with and step size , obtaining for some .