Stable but Wrong: When Learning Stabilizes Away from the Truth

arXiv:2603.21491 · cs.LG · Submitted 2026-03-23 · Read on arXiv

cs.LG

Submitted: 2026-03-23

Updated: 2026-08-27

Comments: 28 pages, 6 figures; substantially revised and refocused version. The title, conceptual framing, theoretical analysis, experiments, presentation, and author list have been extensively updated; supplementary material is included in the appendices

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AUC — 11× in this paper · explained in 2 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Adam — 5× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Metacognition — 2× in this paper · explained in 5 episodes
• Systematic Bias — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Bayesian Framework — 1× in this paper · explained in 3 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks