Learning Can Converge Stably to the Wrong Belief under Latent Reliability

• URL: http://arxiv.org/abs/2603.21491v1
• Date: Mon, 23 Mar 2026 02:28:07 GMT
• Title: Learning Can Converge Stably to the Wrong Belief under Latent Reliability
• Abstract summary: We show that learning algorithms converge stably to incorrect solutions when feedback reliability is unobservable.<n>We propose a Monitor-Trust-Regulator framework that infers reliability from learning dynamics and modulates updates through a slow-timescale trust variable.
• Score: 24.97566911521709
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning systems are typically optimized by minimizing loss or maximizing reward, assuming that improvements in these signals reflect progress toward the true objective. However, when feedback reliability is unobservable, this assumption can fail, and learning algorithms may converge stably to incorrect solutions. This failure arises because single-step feedback does not reveal whether an experience is informative or persistently biased. When information is aggregated over learning trajectories, however, systematic differences between reliable and unreliable regimes can emerge. We propose a Monitor-Trust-Regulator (MTR) framework that infers reliability from learning dynamics and modulates updates through a slow-timescale trust variable. Across reinforcement learning and supervised learning settings, standard algorithms exhibit stable optimization behavior while learning incorrect solutions under latent unreliability, whereas trust-modulated systems reduce bias accumulation and improve recovery. These results suggest that learning dynamics are not only optimization traces but also a source of information about feedback reliability.

Related papers

• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Process Supervision of Confidence Margin for Calibrated LLM Reasoning [52.373121066425455]
  Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability.<n>Yet, outcome-based reward often incentivizes models to be overconfident, leading to hallucinations, unreliable confidence-based control, and unnecessary compute allocation.<n>We introduce Reinforcement Learning with Confidence Margin (textbfRLCM), a calibration-aware RL framework that jointly optimize correctness and confidence reliability.
  arXiv  Detail & Related papers  (2026-04-25T14:40:13Z)
• QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption [7.630511612007769]
  We present QuAIL, a quality-informed training mechanism that incorporates feature reliability priors directly into the learning process.<n>We show that QuAIL consistently improves average performance over neural baselines under both random and value-dependent corruption.
  arXiv  Detail & Related papers  (2026-02-03T16:06:30Z)
• Meta-Cognitive Reinforcement Learning with Self-Doubt and Recovery [25.522943543082363]
  We propose a meta-cognitive reinforcement learning framework that enables an agent to assess, regulate, and recover its learning behavior.<n>The proposed method introduces a meta-trust variable driven by Value Prediction Error Stability (VPES), which modulates learning dynamics via fail-safe regulation and gradual trust recovery.
  arXiv  Detail & Related papers  (2026-01-28T02:43:03Z)
• Learning to Trust Experience: A Monitor-Trust-Regulator Framework for Learning under Unobservable Feedback Reliability [24.97566911521709]
  We study Epistemic Identifiability under Unobservable Reliability (EIUR)<n>Standard robust learning can converge stably yet form high-confidence, systematically wrong beliefs.<n>We propose metacognitive regulation as a practical response: a second, introspective control loop that infers experience credibility from endogenous evidence in the learner's internal dynamics.
  arXiv  Detail & Related papers  (2026-01-14T07:52:14Z)
• Parent-Guided Adaptive Reliability (PGAR): A Behavioural Meta-Learning Framework for Stable and Trustworthy AI [0.0]
  Parent-Guided Adaptive Reliability (PGAR) is a lightweight behavioural meta-learning framework.<n>It adds a supervisory "parent" layer on top of a standard learner to improve stability, calibration, and recovery under disturbances.<n>PGAR functions as a plug-in reliability layer for existing optimization and learning pipelines, supporting interpretable traces in safety-relevant settings.
  arXiv  Detail & Related papers  (2026-01-07T06:02:34Z)
• Optimal Information Combining for Multi-Agent Systems Using Adaptive Bias Learning [0.0]
  Current approaches either ignore these biases, leading to suboptimal decisions, or require expensive calibration procedures that are often infeasible in practice.<n>This paper addresses the fundamental question: when can we learn and correct for these unknown biases to recover near-optimal performance?<n>We develop a theoretical framework that decomposes biases into learnable systematic components and irreducible components.<n>We show that systems with high learnability ratios can recover significant performance, while those with low learnability show minimal benefit.
  arXiv  Detail & Related papers  (2025-10-28T21:52:33Z)
• Aurora: Are Android Malware Classifiers Reliable and Stable under Distribution Shift? [51.12297424766236]
  AURORA is a framework to evaluate malware classifiers based on their confidence quality and operational resilience.<n>AURORA is complemented by a set of metrics designed to go beyond point-in-time performance.<n>The fragility in SOTA frameworks across datasets of varying drift suggests the need for a return to the whiteboard.
  arXiv  Detail & Related papers  (2025-05-28T20:22:43Z)
• Temporal-Difference Variational Continual Learning [77.92320830700797]
  We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.<n>Our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Calibrating Multimodal Learning [94.65232214643436]
  We propose a novel regularization technique, i.e., Calibrating Multimodal Learning (CML) regularization, to calibrate the predictive confidence of previous methods. This technique could be flexibly equipped by existing models and improve the performance in terms of confidence calibration, classification accuracy, and model robustness.
  arXiv  Detail & Related papers  (2023-06-02T04:29:57Z)
• Improving the Performance of Robust Control through Event-Triggered Learning [74.57758188038375]
  We propose an event-triggered learning algorithm that decides when to learn in the face of uncertainty in the LQR problem. We demonstrate improved performance over a robust controller baseline in a numerical example.
  arXiv  Detail & Related papers  (2022-07-28T17:36:37Z)

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.