Should Decision-Makers Reveal Classifiers in Online Strategic Classification?

• URL: http://arxiv.org/abs/2506.01936v1
• Date: Mon, 02 Jun 2025 17:53:49 GMT
• Title: Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
• Authors: Han Shao, Shuo Xie, Kunhe Yang,
• Abstract summary: We study how limiting agents' access to the current classifier affects the decision-maker's performance.<n>In this setting, the decision-maker incurs more mistakes compared to the full-knowledge setting.<n>Our results demonstrate how withholding access to the classifier can backfire and degrade the decision-maker's performance.
• Score: 13.126208719681346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Strategic classification addresses a learning problem where a decision-maker implements a classifier over agents who may manipulate their features in order to receive favorable predictions. In the standard model of online strategic classification, in each round, the decision-maker implements and publicly reveals a classifier, after which agents perfectly best respond based on this knowledge. However, in practice, whether to disclose the classifier is often debated -- some decision-makers believe that hiding the classifier can prevent misclassification errors caused by manipulation. In this paper, we formally examine how limiting the agents' access to the current classifier affects the decision-maker's performance. Specifically, we consider an extended online strategic classification setting where agents lack direct knowledge about the current classifier and instead manipulate based on a weighted average of historically implemented classifiers. Our main result shows that in this setting, the decision-maker incurs $(1-\gamma)^{-1}$ or $k_{\text{in}}$ times more mistakes compared to the full-knowledge setting, where $k_{\text{in}}$ is the maximum in-degree of the manipulation graph (representing how many distinct feature vectors can be manipulated to appear as a single one), and $\gamma$ is the discount factor indicating agents' memory of past classifiers. Our results demonstrate how withholding access to the classifier can backfire and degrade the decision-maker's performance in online strategic classification.

Related papers

• Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information [19.50321703079894]
  We present a novel framework to uncover the weakness of the classifier via counterfactual examples.<n>We test the performance of our prober's misclassification detection and verify its effectiveness on the image classification benchmark datasets.
  arXiv  Detail & Related papers  (2025-03-12T05:05:58Z)
• Bayesian Strategic Classification [11.439576371711711]
  We study the study of partial information release by the learner in strategic classification. We show how such partial information release can, counter-intuitively, benefit the learner's accuracy, despite increasing agents' abilities to manipulate.
  arXiv  Detail & Related papers  (2024-02-13T19:51:49Z)
• Mitigating Word Bias in Zero-shot Prompt-based Classifiers [55.60306377044225]
  We show that matching class priors correlates strongly with the oracle upper bound performance. We also demonstrate large consistent performance gains for prompt settings over a range of NLP tasks.
  arXiv  Detail & Related papers  (2023-09-10T10:57:41Z)
• Anomaly Detection using Ensemble Classification and Evidence Theory [62.997667081978825]
  We present a novel approach for novel detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We use uncertainty for the anomaly detection approach.
  arXiv  Detail & Related papers  (2022-12-23T00:50:41Z)
• Online Selective Classification with Limited Feedback [82.68009460301585]
  We study selective classification in the online learning model, wherein a predictor may abstain from classifying an instance. Two salient aspects of the setting we consider are that the data may be non-realisable, due to which abstention may be a valid long-term action. We construct simple versioning-based schemes for any $mu in (0,1],$ that make most $Tmu$ mistakes while incurring smash$tildeO(T1-mu)$ excess abstention against adaptive adversaries.
  arXiv  Detail & Related papers  (2021-10-27T08:00:53Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)
• Strategic Classification in the Dark [9.281044712121423]
  This paper studies the interaction between a classification rule and the strategic agents it governs. We define the price of opacity as the difference in prediction error between opaque and transparent strategy-robust classifiers. Our experiments show how Hardt et al.'s robust classifier is affected by keeping agents in the dark.
  arXiv  Detail & Related papers  (2021-02-23T10:13:54Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• The Role of Randomness and Noise in Strategic Classification [7.972516140165492]
  We investigate the problem of designing optimal classifiers in the strategic classification setting. We show that in many natural cases, the imposed optimal solution has the structure where players never change their feature vectors. We also show that a noisier signal leads to better equilibria outcomes.
  arXiv  Detail & Related papers  (2020-05-17T21:49:41Z)
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
  Machine learning algorithms are susceptible to data poisoning attacks. We present a unifying view of randomized smoothing over arbitrary functions. We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
  arXiv  Detail & Related papers  (2020-02-07T21:28:30Z)

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.