Stochastic Constrained Monotone Inclusions
Descriptions may be stale. Consult the linked Lean sources.
Stochastic Constrained Monotone Inclusions
We consider a variational inequality for a continuous monotone
operator
The variational inequality is to find
Our assumptions:
Assumption 1 (Constraint set and nearby solution).
The set
Assumption 2 (Monotonicity and generalized Lipschitz
continuity). The operator
Assumption 3 (Stochastic operator oracle). There is
a probability measure
The output
Results
A finite-dimensional real inner-product space; convex
| Result | Oracle complexity | Novelty | Limitations |
|---|---|---|---|
| (1) StochasticConstrainedGeneralizedMonotone
(Ours) |
|||
| (2) AR+SOE (Ji et al. 2026, Thm. 2.2) | (1): Scope extends to
|
(1): Extra logarithmic overhead; high-probability accuracy does not supply (2)’s mean-square residual guarantee. | |
| (3) Derived bound: (Ji et al. 2026, Thm. 2.2), Markov conversion | (1): At |
(1): At fixed confidence,
larger accuracy-logarithm powers: noise term |
|
| (4) Clipped Korpelevich (Vankov et al. 2025, Thm. 4.4) | Expected squared distance to the solution
set; |
(1): Scope covers
monotone operators without quasi-sharpness at |
(1): Requires global monotonicity; (4) also covers nonmonotone quasi-sharp operators. |
| (5) EG (Greenberg and Loizou 2026, Thm. 3.1) | Exact |
(1): Scope allows
finite-variance noise; polynomial rather than exponential |
Abbr: