Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock Prediction
Kasun Dewage, Suranadi De Silva, Shankhadeep Mondal
cs.LG, cs.AI, q-fin.ST
Submitted: 2026-08-09
Updated: 2026-08-11
Comments: Accepted and presented at IJCNN 2026, part of the IEEE World Congress on Computational Intelligence (WCCI 2026)
Code: https://github.com/Kasun-Dewage/Hybrid_
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Chronos: Learning the Language of Time Series
- Layer Normalization
- Gaussian Error Linear Units (GELUs)
- Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
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