Related papers: Prediction-Intervention Games and Invariant Sets

Prediction-Intervention Games and Invariant Sets

URL: http://arxiv.org/abs/2605.16828v1
Date: Sat, 16 May 2026 06:15:41 GMT
Title: Prediction-Intervention Games and Invariant Sets
Abstract summary: We consider the following two-player game: using observational data, the leader chooses a prediction function for a response variable $Y$.<n>The follower then reacts with an intervention on some covariates in the underlying structural causal model to maximize their own objective.<n>We prove, for two common classes of follower objectives, that predictors based on the stable blanket, a specific invariant subset, are always better or as good as those based on the causal parents.
Score: 5.082940690687655
License: http://creativecommons.org/licenses/by/4.0/
Abstract: We consider the following two-player game: using observational data, the leader chooses a prediction function for a response variable $Y$ from given covariates. The follower then reacts with an intervention on some covariates in the underlying structural causal model to maximize their own objective. The leader knows the intervention targets, but may have limited knowledge of the follower's objective. We call this setup a prediction-intervention game, a special case of a Stackelberg game. Finding an optimal strategy for the leader is generally difficult. To avoid severe performance loss, the leader may base their prediction on the causal parents of $Y$, or more generally on an invariant subset of covariates. We prove, for two common classes of follower objectives, that predictors based on the stable blanket, a specific invariant subset, are always better or as good as those based on the causal parents. We further upper bound the leader's post-intervention risk by a worst-case risk over allowed interventions and strengthen existing distribution generalization results to analyze this bound: we give sufficient conditions under which stable-blanket predictors are worst-case optimal, and show by examples that these conditions cannot in general be dropped. Finally, we discuss practical strategies for settings with known and unknown graph, and test them on simulated and real-world data.

Related papers

DrEM: Dual-Side Robust Ensemble Ranking from Noisy User Preference Predictions in Video Recommendation [12.507238526770687]
We propose a dual-side robust ensemble ranking framework called DrEM.<n>Our DrEM introduces a risk-denoising robust loss that corrects empirical risk using estimated preference flip probability.<n>It samples perturbations from the distribution of prediction noise and introduces a preference-preserving ranking consistency regularizer to improve feature-side output stability.
arXiv Detail & Related papers (2026-08-13T03:36:09Z)
Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap [75.41420283374737]
Overlap is a key condition for causal treatment effect estimation.<n>We propose a class of feature representations called deconfounding scores.<n>We show that prognostic scores are overlap-optimal within this class.
arXiv Detail & Related papers (2026-04-01T12:19:42Z)
Generalisation and benign over-fitting for linear regression onto random functional covariates [4.344644788142548]
We study theoretical predictive performance of ridge and ridge-less least-squares regression.<n>We derive convergence rates in regimes where $p$ grows fast relative to $n$.
arXiv Detail & Related papers (2025-08-19T15:01:20Z)
Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions [51.88828388720111]
We describe a robust planning method for autonomous driving that mixes normal and adversarial agent predictions.<n>We generate a distribution of adversarial predictions by biasing the diffusion model at test time to generate predictions that are likely to collide with a candidate plan.<n>We show the effectiveness of our method on single-agent and multi-agent jaywalking scenarios as well as a red light violation scenario.
arXiv Detail & Related papers (2025-05-18T09:44:57Z)
Indiscriminate Disruption of Conditional Inference on Multivariate Gaussians [60.22542847840578]
Despite advances in adversarial machine learning, inference for Gaussian models in the presence of an adversary is notably understudied. We consider a self-interested attacker who wishes to disrupt a decisionmaker's conditional inference and subsequent actions by corrupting a set of evidentiary variables. To avoid detection, the attacker also desires the attack to appear plausible wherein plausibility is determined by the density of the corrupted evidence.
arXiv Detail & Related papers (2024-11-21T17:46:55Z)
Sequential Manipulation Against Rank Aggregation: Theory and Algorithm [119.57122943187086]
We leverage an online attack on the vulnerable data collection process. From the game-theoretic perspective, the confrontation scenario is formulated as a distributionally robust game. The proposed method manipulates the results of rank aggregation methods in a sequential manner.
arXiv Detail & Related papers (2024-07-02T03:31:21Z)
High-Dimensional Prediction for Sequential Decision Making [9.684829814477526]
We study the problem of making predictions of an adversarially chosen high-dimensional state that are unbiased subject to an arbitrary collection of conditioning events. We give efficient algorithms for solving this problem, as well as a number of applications that stem from choosing an appropriate set of conditioning events.
arXiv Detail & Related papers (2023-10-26T17:59:32Z)
When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
arXiv Detail & Related papers (2023-07-06T04:13:57Z)
Bagging in overparameterized learning: Risk characterization and risk monotonization [2.6534407766508177]
We study the prediction risk of variants of bagged predictors under the proportionals regime. Specifically, we propose a general strategy to analyze the prediction risk under squared error loss of bagged predictors.
arXiv Detail & Related papers (2022-10-20T17:45:58Z)
Prediction Sets Adaptive to Unknown Covariate Shift [18.105704797438417]
We show that prediction sets with finite-sample coverage guarantee are uninformative. We propose a novel flexible distribution-free method, PredSet-1Step, to efficiently construct prediction sets.
arXiv Detail & Related papers (2022-03-11T17:53:14Z)
Multi-label Chaining with Imprecise Probabilities [0.0]
We present two different strategies to extend the classical multi-label chaining approach to handle imprecise probability estimates. The main reasons one could have for using such estimations are (1) to make cautious predictions when a high uncertainty is detected in the chaining and (2) to make better precise predictions by avoiding biases caused in early decisions in the chaining. Our experimental results on missing labels, which investigate how reliable these predictions are in both approaches, indicate that our approaches produce relevant cautiousness on those hard-to-predict instances where the precise models fail.
arXiv Detail & Related papers (2021-07-15T16:43:31Z)
Offline Contextual Bandits with Overparameterized Models [52.788628474552276]
We ask whether the same phenomenon occurs for offline contextual bandits. We show that this discrepancy is due to the emphaction-stability of their objectives. In experiments with large neural networks, this gap between action-stable value-based objectives and unstable policy-based objectives leads to significant performance differences.
arXiv Detail & Related papers (2020-06-27T13:52:07Z)

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