# Stabilizing Performative Feedback Loops with Minimal Model Deployments

arXiv: https://arxiv.org/abs/2609.14065 · HTML: https://mlsanity.com/paper/2609.14065/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Outside the Echo Chamber: Optimizing the Performative Risk](https://mlsanity.com/paper/2102.08570/) (2021)
- [Stochastic Optimization for Performative Prediction](https://mlsanity.com/paper/2006.06887/) (2020)
- [Performative Prediction in a Stateful World](https://mlsanity.com/paper/2011.03885/) (2020)
- [How to Learn when Data Reacts to Your Model: Performative Gradient Descent](https://mlsanity.com/paper/2102.07698/) (2021)
- [Stochastic optimization with decision-dependent distributions](https://mlsanity.com/paper/2011.11173/) (2020)
- [An Improved Cutting Plane Method for Convex Optimization, Convex-Concave Games and its Applications](https://mlsanity.com/paper/2004.04250/) (2020)
- [Multiplayer Performative Prediction: Learning in Decision-Dependent Games](https://mlsanity.com/paper/2201.03398/) (2022)
- [Regret Minimization with Performative Feedback](https://mlsanity.com/paper/2202.00628/) (2022)
- [Difficult Lessons on Social Prediction from Wisconsin Public Schools](https://mlsanity.com/paper/2304.06205/) (2023)
- [Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos](https://mlsanity.com/paper/2201.10483/) (2022)
- [Making Decisions under Outcome Performativity](https://mlsanity.com/paper/2210.01745/) (2022)
- [Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agents](https://mlsanity.com/paper/2209.03811/) (2022)
- [Forecast Hedging and Calibration](https://mlsanity.com/paper/2210.07169/) (2022)
- [Plug-in Performative Optimization](https://mlsanity.com/paper/2305.18728/) (2023)
- [Lower Bounds on the Oracle Complexity of Nonsmooth Convex Optimization via Information Theory](https://mlsanity.com/paper/1407.5144/) (2014)
- [Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games](https://mlsanity.com/paper/2412.20291/) (2024)
- [Revisiting the Predictability of Performative, Social Events](https://mlsanity.com/paper/2503.11713/) (2025)
- [An engine not a camera: Measuring performative power of online search](https://mlsanity.com/paper/2405.19073/) (2024)
- [In Defense of Defensive Forecasting](https://mlsanity.com/paper/2506.11848/) (2025)
- [The Stability of Online Algorithms in Performative Prediction](https://mlsanity.com/paper/2602.24207/) (2026)
- [On the Computational Complexity of Performative Prediction](https://mlsanity.com/paper/2601.20180/) (2026)
- [Partially Performative Prediction](https://mlsanity.com/paper/2606.07890/) (2026)
- [Retraining Seeks Stable Signals](https://mlsanity.com/paper/2607.15623/) (2026)

## Abstract (arXiv)

When algorithmic predictions inform people's decisions, the models we deploy are performative and actively shape the data we see. This feedback loop between algorithms and their broader environments introduces a challenge in the mechanics of social prediction: If different predictive models induce different distributions, is it possible to efficiently learn a prediction rule that is optimal for the distribution that it induces? Formally, this solution concept is known as performative stability. A core challenge in learning a performatively stable predictor is that, unlike supervised learning where distributions are fixed, the learner must deploy different predictors and observe their induced distributions. The main contribution of our work is a new algorithmic procedure that, in the high-accuracy regime, finds a performatively stable model in nearly the minimum number of model deployments without making any assumptions regarding how predictions shape distributions. In particular, our procedure succeeds at finding a randomized performatively stable predictor using exponentially fewer model deployments than prior approaches. Our second main contribution is a structural result showing how this recent randomized notion of stability achieved by our algorithm can be derandomized into a single predictor satisfying the prior deterministic notion if one is willing to assume that the loss is well-conditioned and that performative effects are weak, as in early work in this area. On a technical level, our results come from building on an underexplored technical connection between performative stability and expected variational inequalities.