Neural networks become centroid classifiers when trained on heavily corrupted inputs

arXiv:2606.11319 · cs.LG, cond-mat.dis-nn · Submitted 2026-06-09 · Read on arXiv

cs.LG, cond-mat.dis-nn

Submitted: 2026-06-09

Updated: 2026-10-22

Terminology

• Robustness — 2× in this paper · explained in 6 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks