Unlearning Offline Stochastic Multi-Armed Bandits

• URL: http://arxiv.org/abs/2605.00638v1
• Date: Fri, 01 May 2026 13:20:13 GMT
• Title: Unlearning Offline Stochastic Multi-Armed Bandits
• Abstract summary: We aim to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining.<n>We conduct a systematic study of both single- and multi-source unlearning scenarios under two data-generation models.<n>We propose adaptive algorithms that switch between them according to the data regime and privacy constraint.
• Score: 25.148290301136047
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining. Prior work has mainly studied unsupervised / supervised machine unlearning, leaving unlearning for sequential decision-making systems far less understood. We initiate the first study of a foundational sequential decision-making problem: offline stochastic multi-armed bandits (MAB). We formalize the privacy constraint for offline MAB and measure utility by the post-unlearning decision quality. We conduct a systematic study of both single- and multi-source unlearning scenarios under two data-generation models, the fixed-sample model and the distribution model. For these settings, our algorithmic design is built on two canonical base algorithms: Gaussian mechanism and rollback, and we propose adaptive algorithms that switch between them according to the data regime and privacy constraint. We further introduce a mixing procedure that elucidates the rationale behind these baselines. We provide performance guarantees across the above settings and establish lower bounds under both dataset models. Experiments validate the predicted tradeoffs and demonstrate the effectiveness of the proposed methods.

Related papers

• Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints [64.15709757611369]
  We propose a new self-supervised pre-training approach to dealing with heterogeneous data.<n>The proposed approach can significantly improve the adaptivity of the self-supervised pre-trained model for the downstream supervised fine-tuning tasks.
  arXiv  Detail & Related papers  (2025-08-27T15:48:50Z)
• Auditing Approximate Machine Unlearning for Differentially Private Models [14.700807572189412]
  We propose a holistic approach to auditing unlearned and retained samples' privacy risks after applying approximate unlearning algorithms.<n>Our experimental findings indicate that existing approximate machine unlearning algorithms may inadvertently compromise the privacy of retained samples for differentially private models.
  arXiv  Detail & Related papers  (2025-08-26T04:29:33Z)
• Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation [23.668928015009087]
  Machine unlearning aims to remove the influence of specific samples from a trained model.<n>Existing unlearning algorithms depend on the remaining data to prevent this issue.<n>This paper presents a novel framework, ZS-PAG, to fill this gap.
  arXiv  Detail & Related papers  (2025-07-29T12:16:55Z)
• Preference-Based Multi-Agent Reinforcement Learning: Data Coverage and Algorithmic Techniques [65.55451717632317]
  We study Preference-Based Multi-Agent Reinforcement Learning (PbMARL)<n>We identify the Nash equilibrium from a preference-only offline dataset in general-sum games.<n>Our findings underscore the multifaceted approach required for PbMARL.
  arXiv  Detail & Related papers  (2024-09-01T13:14:41Z)
• Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond [13.864609787260298]
  We propose an uncertainty-aware memory-based approach to solve catastrophic forgetting.<n>We retrieve samples with specific characteristics, and - by retraining the model on such samples - we demonstrate the potential of this approach.
  arXiv  Detail & Related papers  (2024-05-29T09:29:39Z)
• Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning [2.9158689853305693]
  We consider a model-based reinforcement learning algorithm that infers the system dynamics from the available data and performs policy optimization on imaginary model rollouts. This approach is vulnerable to exploiting model errors which can lead to catastrophic failures on the real system. We show that better performance can be obtained with a single well-calibrated autoregressive model on the D4RL benchmark.
  arXiv  Detail & Related papers  (2024-02-05T10:18:15Z)
• Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraints [51.12047280149546]
  A direct approach for obtaining a fair predictive model is to train the model through optimizing its prediction performance subject to fairness constraints. We formulate the training problem of a fairness-aware machine learning model as an AUC optimization problem subject to a class of AUC-based fairness constraints. We demonstrate the effectiveness of our approach on real-world data under different fairness metrics.
  arXiv  Detail & Related papers  (2022-12-23T22:29:08Z)
• Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control [67.52000805944924]
  Learn then Test (LTT) is a framework for calibrating machine learning models. Our main insight is to reframe the risk-control problem as multiple hypothesis testing. We use our framework to provide new calibration methods for several core machine learning tasks with detailed worked examples in computer vision.
  arXiv  Detail & Related papers  (2021-10-03T17:42:03Z)
• Rank-Based Multi-task Learning for Fair Regression [9.95899391250129]
  We develop a novel learning approach for multi-taskart regression models based on a biased dataset. We use a popular non-parametric oracle-based non-world multipliers dataset.
  arXiv  Detail & Related papers  (2020-09-23T22:32:57Z)
• Control as Hybrid Inference [62.997667081978825]
  We present an implementation of CHI which naturally mediates the balance between iterative and amortised inference. We verify the scalability of our algorithm on a continuous control benchmark, demonstrating that it outperforms strong model-free and model-based baselines.
  arXiv  Detail & Related papers  (2020-07-11T19:44:09Z)
• Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data [66.78671826743884]
  The distributionally robust optimization framework is considered for training a parametric model. The objective is to endow the trained model with robustness against adversarially manipulated input data. Proposed algorithms offer robustness with little overhead.
  arXiv  Detail & Related papers  (2020-07-07T18:25:25Z)

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.