activity
20242026
collaborators

6 papers

cs.LG2026

Deployment-Side Adaptiveness in Multi-Horizon Volatility Forecasting

Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho

In financial forecasting, predictive performance depends not only on which model is trained, but also on how the trained model is deployed. We study this issue in multi-horizon vol…

cs.LG2026

Exposure Bias as Epistemic Underidentification in Recursive Forecasting

Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho

Recursive multi-step forecasting is usually framed as distribution shift: models are trained on observed histories but deployed on their own predictions. We show this framing is in…

cs.LG2026

Expectations vs. Realities: The Cost of MSE-Optimal Forecasting Under Conditional Uncertainty

Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho

Multi-step time series forecasting (MSF) is commonly evaluated using point-wise error metrics such as mean squared error (MSE), implicitly treating the conditional mean as a suffic…

cs.LG2025

Epistemic Error Decomposition for Multi-step Time Series Forecasting: Rethinking Bias-Variance in Recursive and Direct Strategies

Riku Green, Huw Day, Zahraa S. Abdallah +1

Multi-step forecasting is often described through a simple rule of thumb: recursive strategies are said to have high bias and low variance, while direct strategies are said to have…

cs.LG2024

Stratify: Unifying Multi-Step Forecasting Strategies

Riku Green, Grant Stevens, Zahraa Abdallah +1

A key aspect of temporal domains is the ability to make predictions multiple time steps into the future, a process known as multi-step forecasting (MSF). At the core of this proces…

cs.LG2024

Topology Only Pre-Training: Towards Generalised Multi-Domain Graph Models

Alex O. Davies, Riku W. Green, Nirav S. Ajmeri +1

The principal benefit of unsupervised representation learning is that a pre-trained model can be fine-tuned where data or labels are scarce. Existing approaches for graph represent…