Spectral Overfitting in Noisy Linear Probing of Pretrained Representations
cs.LG, cs.AI
Submitted: 2026-03-02
Updated: 2026-09-22
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels
- Limitations of Neural Collapse for Understanding Generalization in Deep Learning
- Convergent Learning: Do different neural networks learn the same representations?
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- The Intrinsic Dimension of Images and Its Impact on Learning
- Defending against Adversarial Images using Basis Functions Transformations
- Opening the Black Box of Deep Neural Networks via Information
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