In-Context Time Series Classification with Random Convolutional Features

arXiv:2607.19234 · cs.LG · Submitted 2026-07-21 · Read on arXiv

cs.LG

Submitted: 2026-07-21

Updated: 2026-10-05

Code: https://github.com/joschac/masht

Terminology

• Foundation Model — 3× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes

Sources

• TabPFN-3: Technical Report
• TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model
• The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification
• RocketPFN: Accurate Time Series Classification via In-Context Learning
• TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification

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