# Stochastic Minimax Optimization on Theoretical Analysis Source: [Stochastic Minimax Optimization on Theoretical Analysis]() Collection index: [llms.txt]() Data updated: 2026-06-24T07:12:42.043Z Theoretical analysis of algorithms for Stochastic Minimax Optimization, focusing on performance bounds such as Sample Complexity. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Stochastic Minimax Optimization | | Dataset (including any stated split) | Theoretical Analysis | | Metric | Sample Complexity | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Sample Complexity](): Lower is better; unit: SCALAR. ## Recorded results | Method | Sample Complexity | Result date | Report paper | | --- | --- | --- | --- | | SGDA | -4 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | Stoc-Smoothed-AGDA | -4 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | SREDA | -3 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | DM-HSGD | -3 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | MSGDA | -3 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | HCMM-1 | -3 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | HCMM-2 | -3 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | Extra-Momentum | 1 | Not recorded | 68fa5d6d1e209131ce9da1a8 | | VR-AGDA | 9 | Not recorded | 68fa5d6d1e209131ce9da1a8 | ### SGDA Sample Complexity: -4. Result ID: 6a3b834dfbc373592c4354c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex–SC","Lipschitz Condition":"Lipschitz risk gradient","Learning Rates":"Constant"}. This record does not assert independent reproduction. ### Stoc-Smoothed-AGDA Sample Complexity: -4. Result ID: 6a3b834dfbc373592c4354c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex–PL","Lipschitz Condition":"Lipschitz risk gradient","Learning Rates":"Constant"}. This record does not assert independent reproduction. ### SREDA Sample Complexity: -3. Result ID: 6a3b834dfbc373592c4354c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex-SC","Lipschitz Condition":"Expected Lipschitz loss gradient","Learning Rates":"Constant"}. This record does not assert independent reproduction. ### DM-HSGD Sample Complexity: -3. Result ID: 6a3b834dfbc373592c4354c6. [Reporting paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex-SC","Lipschitz Condition":"Lipschitz loss gradient","Learning Rates":"Constant"}. This record does not assert independent reproduction. ### MSGDA Sample Complexity: -3. Result ID: 6a3b834dfbc373592c4354c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex–PL","Lipschitz Condition":"Lipschitz loss gradient","Learning Rates":"Diminishing"}. This record does not assert independent reproduction. ### HCMM-1 Sample Complexity: -3. Result ID: 6a3b834dfbc373592c4354c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex–PL","Lipschitz Condition":"Lipschitz risk gradient and Hessian","Learning Rates":"Nonlinear via clipping"}. This record does not assert independent reproduction. ### HCMM-2 Sample Complexity: -3. Result ID: 6a3b834dfbc373592c4354ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Nonconvex–PL","Lipschitz Condition":"Lipschitz risk gradient and Hessian","Learning Rates":"Nonlinear via normalization"}. This record does not assert independent reproduction. ### Extra-Momentum Sample Complexity: 1. Result ID: 6a3b834dfbc373592c4354c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cost Structure":"Strongly Monotone","Lipschitz Condition":"Lipschitz risk gradient","Learning Rates":"Constant"}. This record does not assert independent reproduction. ### VR-AGDA Sample Complexity: 9. Result ID: 6a3b834dfbc373592c4354c3. [Reporting paper]() Recorded evaluation configuration: {"Cost Structure":"PL-PL","Lipschitz Condition":"Lipschitz loss gradient","Learning Rates":"Constant"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.