67 citations · 135 across the 26 of their papers we have counts for
5 papers · 1 filter
DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
Kieran Wood, Stefan Zohren, Stephen J. Roberts
We introduce DeRegiME -- Deep Regime Mixture of Experts -- a direct multi-horizon probabilistic forecaster that separates latent uncertainty regimes from the underlying signal and…
On Sequential Bayesian Inference for Continual Learning
Samuel Kessler, Adam Cobb, Tim G. J. Rudner +2
Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revis…
Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture
Kieran Wood, Sven Giegerich, Stephen Roberts +1
We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike…
Same State, Different Task: Continual Reinforcement Learning without Interference
Samuel Kessler, Jack Parker-Holder, Philip Ball +2
Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL i…
Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
Zihao Zhang, Stefan Zohren
We design multi-horizon forecasting models for limit order book (LOB) data by using deep learning techniques. Unlike standard structures where a single prediction is made, we adopt…