Who is Afraid of Minimal Revision?

• URL: http://arxiv.org/abs/2511.22386v1
• Date: Thu, 27 Nov 2025 12:15:43 GMT
• Title: Who is Afraid of Minimal Revision?
• Abstract summary: We show that minimal revision is still a successful learning method in a wide range of situations.<n>We characterize the prior plausibility assignments that enable one to learn via minimal revision.<n>We show that not all of our results still hold when learning from possibly erroneous information.
• Score: 1.396448286983864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The principle of minimal change in belief revision theory requires that, when accepting new information, one keeps one's belief state as close to the initial belief state as possible. This is precisely what the method known as minimal revision does. However, unlike less conservative belief revision methods, minimal revision falls short in learning power: It cannot learn everything that can be learned by other learning methods. We begin by showing that, despite this limitation, minimal revision is still a successful learning method in a wide range of situations. Firstly, it can learn any problem that is finitely identifiable. Secondly, it can learn with positive and negative data, as long as one considers finitely many possibilities. We then characterize the prior plausibility assignments (over finitely many possibilities) that enable one to learn via minimal revision, and do the same for conditioning and lexicographic upgrade. Finally, we show that not all of our results still hold when learning from possibly erroneous information.

Related papers

• Partial Feedback Online Learning [88.27143767009376]
  We study a new learning protocol, termed partial-feedback online learning.<n>Each instance admits a set of acceptable labels, but the learner observes only one acceptable label per round.
  arXiv  Detail & Related papers  (2026-01-29T09:39:11Z)
• Existing Large Language Model Unlearning Evaluations Are Inconclusive [105.55899615056573]
  We show that some evaluations introduce substantial new information into the model, potentially masking true unlearning performance.<n>We demonstrate that evaluation outcomes vary significantly across tasks, undermining the generalizability of current evaluation routines.<n>We propose two principles for future unlearning evaluations: minimal information injection and downstream task awareness.
  arXiv  Detail & Related papers  (2025-05-31T19:43:00Z)
• From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization [46.78723722220735]
  Recent unlearning methods for LLMs are vulnerable to relearning attacks.<n>We make the surprising discovery that forget-set accuracy can recover from around 50% post-unlearning to nearly 100% with fine-tuning on just the retain set.<n>We propose a new class of methods that achieve state-of-the-art resistance to relearning attacks.
  arXiv  Detail & Related papers  (2025-05-28T12:53:08Z)
• Do Your Best and Get Enough Rest for Continual Learning [8.17916139651372]
  According to the forgetting curve theory, we can enhance memory retention by learning extensive data and taking adequate rest.<n>We introduce the view-batch model that adjusts the learning schedules to optimize the recall interval between retraining the same samples.<n>We empirically show that these approaches are aligned with the forgetting curve theory, which can enhance long-term memory.
  arXiv  Detail & Related papers  (2025-03-24T06:08:37Z)
• Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge [93.54427119091174]
  We propose outDated ISsue aware deCOding to enhance the performance of edited models on reasoning questions. We capture the difference in the probability distribution between the original and edited models. We amplify the difference of the token prediction in the edited model to alleviate the outdated issue.
  arXiv  Detail & Related papers  (2024-06-05T03:00:15Z)
• Human-Aware Belief Revision: A Cognitively Inspired Framework for Explanation-Guided Revision of Human Models [4.2356833681644055]
  We introduce Human-Aware Belief Revision, a cognitively-inspired framework for modeling human belief revision dynamics. We conduct two human-subject studies to empirically evaluate our framework under real-world scenarios. Our findings support our hypotheses and provide insights into the strategies people employ when resolving inconsistencies, offering some guidance for developing more effective human-aware AI systems.
  arXiv  Detail & Related papers  (2024-05-29T16:20:51Z)
• Can we forget how we learned? Doxastic redundancy in iterated belief revision [0.0]
  Forgetting a belief acquisition episode may not cause information loss because of the others.<n>Checking whether it does is not obvious, as the contribution of each belief revision is not isolated from the others.<n>An algorithm for checking whether forgetting reduces information is given for a number of iterated belief revision operators.
  arXiv  Detail & Related papers  (2024-02-23T17:09:04Z)
• Natural revision is contingently-conditionalized revision [0.0]
  Natural revision seems so natural: it changes beliefs as little as possible.<n>Yet, some counterexamples show it wrong.<n>This is right in some cases and wrong in others.
  arXiv  Detail & Related papers  (2023-09-22T06:52:30Z)
• Ticketed Learning-Unlearning Schemes [57.89421552780526]
  We propose a new ticketed model for learning--unlearning. We provide space-efficient ticketed learning--unlearning schemes for a broad family of concept classes.
  arXiv  Detail & Related papers  (2023-06-27T18:54:40Z)
• Imitating Past Successes can be Very Suboptimal [145.70788608016755]
  We show that existing outcome-conditioned imitation learning methods do not necessarily improve the policy. We show that a simple modification results in a method that does guarantee policy improvement. Our aim is not to develop an entirely new method, but rather to explain how a variant of outcome-conditioned imitation learning can be used to maximize rewards.
  arXiv  Detail & Related papers  (2022-06-07T15:13:43Z)
• Universal Online Learning with Unbounded Losses: Memory Is All You Need [10.839359285994636]
  A given learning rule is said to be optimistically universal if it achieves a low long-run average loss. Hanke posed as an open problem whether, for every unbounded loss, the family of processes admitting universal learning are precisely those having a finite number of distinct values. As a consequence, this also offers a dramatically simpler formulation of an optimistically universal learning rule for any unbounded loss.
  arXiv  Detail & Related papers  (2022-01-21T22:03:18Z)
• Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship [54.73817402934303]
  We propose Experience Continual Replay (ERR), a bi-level learning framework to adaptively tune task-wise to achieve a better stability plasticity' tradeoff. ERR can consistently improve the performance of all baselines and surpass current state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-31T12:05:22Z)
• Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning [76.98364915566292]
  A common practice is to train a model on the base set first and then transfer to novel classes through fine-tuning. We propose to transfer partial knowledge by freezing or fine-tuning particular layer(s) in the base model. We conduct extensive experiments on CUB and mini-ImageNet to demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2021-02-08T03:27:05Z)

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.