Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling

arXiv:2510.08944 · cs.LG · Submitted 2025-10-10 · Read on arXiv

cs.LG

Submitted: 2025-10-10

Updated: 2026-10-01

Terminology

• Computational overhead — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Variability Aware Recursive Neural Network — 1× in this paper

Sources

• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Modern strategies for time series regression
• The Design and Sensitivity of JUNO's scintillator radiopurity pre-detector OSIRIS
• Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• A Comprehensive Survey of Deep Learning for Time Series Forecasting: Architectural Diversity and Open Challenges
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• N-BEATS: Neural basis expansion analysis for interpretable 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