Researcher
Arrykrishna Mootoovaloo
He builds models that take uncertainty seriously, making expensive computations fast and turning noisy data into sound decisions. Trained as a researcher, he brings scientific rigour to industry, where models must be both principled and fast enough to act on.
Experience
- Fuse Energy
- QRT
- Huawei
- University of Oxford
Education
- Imperial College London
- University of Cape Town
Focus areas
Probabilistic machine learning
Normalising flows, Gaussian Processes and principled uncertainty quantification.
Deep learning and fast inference
Deep learning pipelines, diffusion models and emulators that make expensive computations fast.
Quantitative research
Hedging models, signal detection and rigorous backtesting for energy and financial markets.
AI research
Generative models for image editing, multi-task learning and few-shot learning, from industrial R&D to academic research.
Recent publications
All publications →-
2026
-
2024
-
2024
★ Assessment of Gradient-Based Samplers in Standard Cosmological Likelihoods
MNRASNeurIPS 2024
Recent writing
All posts →-
Deciding how much to hedge, and shaping forward curves.
-
Momentum strategies, turnover control and honest backtesting.
-
Running AI on phones and edge devices: compilation and quantisation.
-
Fast joint analyses with normalising flows.