The Decoupled Risk Landscape in Performative Prediction

• URL: http://arxiv.org/abs/2506.09044v1
• Date: Tue, 10 Jun 2025 17:58:39 GMT
• Title: The Decoupled Risk Landscape in Performative Prediction
• Authors: Javier Sanguino, Thomas Kehrenberg, Jose A. Lozano, Novi Quadrianto,
• Abstract summary: Performative Prediction addresses scenarios where deploying a model induces a distribution shift in the input data.<n>We introduce a simple decoupled risk visualization method inspired in the two-step process that performative prediction is.<n>We introduce a novel setting - extended Performative Prediction - which captures scenarios where the distribution reacts to a model different from the decision-making one.
• Score: 3.904855396113132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Performative Prediction addresses scenarios where deploying a model induces a distribution shift in the input data, such as individuals modifying their features and reapplying for a bank loan after rejection. Literature has had a theoretical perspective giving mathematical guarantees for convergence (either to the stable or optimal point). We believe that visualization of the loss landscape can complement this theoretical advances with practical insights. Therefore, (1) we introduce a simple decoupled risk visualization method inspired in the two-step process that performative prediction is. Our approach visualizes the risk landscape with respect to two parameter vectors: model parameters and data parameters. We use this method to propose new properties of the interest points, to examine how existing algorithms traverse the risk landscape and perform under more realistic conditions, including strategic classification with non-linear models. (2) Building on this decoupled risk visualization, we introduce a novel setting - extended Performative Prediction - which captures scenarios where the distribution reacts to a model different from the decision-making one, reflecting the reality that agents often lack full access to the deployed model.

Related papers

• Automated Modeling Method for Pathloss Model Discovery [1.7373039830910548]
  This paper proposes a novel approach that accelerates the discovery of path loss models while maintaining interpretability.<n>We examine two techniques: one based on Deep Symbolic Regression, offering full interpretability, and the second based on Kolmogorov-Arnold Networks, providing two levels of interpretability.<n>Our results show that Kolmogorov-Arnold Networks achieve the coefficient of determination value R2 close to 1 with minimal prediction error, while Deep Symbolic Regression generates compact models with moderate accuracy.
  arXiv  Detail & Related papers  (2025-05-29T12:04:07Z)
• Seeing Through Risk: A Symbolic Approximation of Prospect Theory [0.0]
  We propose a novel symbolic modeling framework for decision-making under risk.<n>Our approach replaces opaque utility curves and probability weighting functions with transparent, effect-size-guided features.<n>We mathematically formalize the method, demonstrate its ability to replicate well-known framing and loss-aversion phenomena, and provide an end-to-end empirical validation on synthetic datasets.
  arXiv  Detail & Related papers  (2025-04-20T01:44:54Z)
• A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Prediction [7.306417438683524]
  We present a new paradigm for evaluating egocentric pedestrian trajectory prediction algorithms. We show that our approach achieves significant improvement by up to 40% in challenging scenarios.
  arXiv  Detail & Related papers  (2023-10-16T14:08:34Z)
• Performative Prediction with Bandit Feedback: Learning through Reparameterization [23.039885534575966]
  performative prediction is a framework for studying social prediction in which the data distribution itself changes in response to the deployment of a model. We develop a reparametization that reparametrizes the performative prediction objective as a function of induced data distribution.
  arXiv  Detail & Related papers  (2023-05-01T21:31:29Z)
• Mitigating multiple descents: A model-agnostic framework for risk monotonization [84.6382406922369]
  We develop a general framework for risk monotonization based on cross-validation. We propose two data-driven methodologies, namely zero- and one-step, that are akin to bagging and boosting.
  arXiv  Detail & Related papers  (2022-05-25T17:41:40Z)
• Joint Forecasting of Panoptic Segmentations with Difference Attention [72.03470153917189]
  We study a new panoptic segmentation forecasting model that jointly forecasts all object instances in a scene. We evaluate the proposed model on the Cityscapes and AIODrive datasets.
  arXiv  Detail & Related papers  (2022-04-14T17:59:32Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Approximate Regions of Attraction in Learning with Decision-Dependent Distributions [11.304363655760513]
  We analyze repeated risk minimization as the trajectories of the gradient flows of performative risk minimization. We provide conditions to characterize the region of attraction for the various equilibria in this setting. We introduce the notion of performative alignment, which provides a geometric condition on the convergence of repeated risk minimization to performative risk minimizers.
  arXiv  Detail & Related papers  (2021-06-30T18:38:08Z)
• MINIMALIST: Mutual INformatIon Maximization for Amortized Likelihood Inference from Sampled Trajectories [61.3299263929289]
  Simulation-based inference enables learning the parameters of a model even when its likelihood cannot be computed in practice. One class of methods uses data simulated with different parameters to infer an amortized estimator for the likelihood-to-evidence ratio. We show that this approach can be formulated in terms of mutual information between model parameters and simulated data.
  arXiv  Detail & Related papers  (2021-06-03T12:59:16Z)
• Attentional Prototype Inference for Few-Shot Segmentation [128.45753577331422]
  We propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. We conduct extensive experiments on four benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art prototype-based methods.
  arXiv  Detail & Related papers  (2021-05-14T06:58:44Z)
• Forethought and Hindsight in Credit Assignment [62.05690959741223]
  We work to understand the gains and peculiarities of planning employed as forethought via forward models or as hindsight operating with backward models. We investigate the best use of models in planning, primarily focusing on the selection of states in which predictions should be (re)-evaluated.
  arXiv  Detail & Related papers  (2020-10-26T16:00:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.