In-context Learning of Single-index Targets: Comparing Kernel and Feature Learners
cs.LG, cond-mat.dis-nn, stat.ML
Submitted: 2026-10-01
Updated: 2026-10-01
Terminology
Sources
- Softmax $\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent
- The Rules-and-Facts Model for Simultaneous Generalization and Memorization in Neural Networks
- Spherical Harmonics in p Dimensions
- When can in-context learning generalize out of task distribution?
- Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime
- The Effect of Training Task Diversity on In-Context Learning through the Lens of Low-Dimensional Subspaces
- Spectrum of inner-product kernel matrices in the polynomial regime and multiple descent phenomenon in kernel ridge regression
- Training Dynamics of In-Context Learning in Linear Attention
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