Research map / Bandits and online learning / Online convex optimization and games
Zero-Regret Performative Prediction Under Inequality Constraints
Wenjing Yan, Xuanyu Cao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add the performative-gradient term to the PD-PS gradient (ablation) | Primal-dual algorithm · Multi-task linear regression | relative time-average regret | Improved |
| add the performative-gradient term to the PD-PS gradient (ablation) | Primal-dual algorithm · Multi-task linear regression | decision deviation | Improved |
| add the performative-gradient term to the PD-PS gradient (ablation) | Primal-dual algorithm · Multi-asset portfolio | relative time-average regret | Improved |
| add the performative-gradient term to the PD-PS gradient (ablation) | Primal-dual algorithm · Multi-asset portfolio | decision deviation | Improved |
| increase sensitivity from \varepsilon = 1 to \varepsilon = 10 | PD-PS · Multi-task linear regression and multi-asset portfolio | relative time-average regret | Hurt |
| estimate the performative effect rather than assume perfect knowledge of A | APDA · Multi-task linear regression and multi-asset portfolio | relative time-average regret | No clear effect |
| use the adaptive primal-dual algorithm with location-family gradient approximation | Constrained performative prediction · Constrained performative prediction | regret | Improved |
| use the adaptive primal-dual algorithm with location-family gradient approximation | Constrained performative prediction · Constrained performative prediction | constraint violation | Improved |
Closest papers by meaning
- Performative Prediction with Bandit Feedback: Learning through Reparameterization (ICML 2024 · similarity 0.90)
- Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss (NeurIPS 2024 · similarity 0.89)
- Tight Lower Bounds and Improved Convergence in Performative Prediction (NeurIPS 2025 · similarity 0.87)
- Distributionally Robust Performative Optimization (NeurIPS 2025 · similarity 0.87)
- The Stability of Online Algorithms in Performative Prediction (NeurIPS 2026 · similarity 0.87)
- Optimal Classification under Performative Distribution Shift (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
