A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt
cs.LG, math.ST, stat.ML, stat.TH
Submitted: 2026-06-14
Updated: 2026-06-14
Project page: http://probml.github.io/book1
Terminology
Sources
- Pac-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning
- Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
- Test time training enhances in-context learning of nonlinear functions
- Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
- Amortized In-Context Bayesian Posterior Estimation
- In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning
- Test-Time Training Done Right
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