Theo Brown
@theo-brown.bsky.social
PhD student UCL / UKAEA | Probabilistic ML | Safe control | Nuclear fusion
Huge kudos to the team for their hard work in delivering this high-quality contribution to the community. Open-source fusion modelling just got a big boost!
Paper:
pubs.aip.org/aip/pop/arti...
Paper:
pubs.aip.org/aip/pop/arti...
FreeGSNKE: A Python-based dynamic free-boundary toroidal plasma equilibrium solver
We present a Python-based numerical solver for the two-dimensional dynamic plasma equilibrium problem. We model the time evolution of toroidally symmetric free-
pubs.aip.org
January 16, 2025 at 11:46 AM
Huge kudos to the team for their hard work in delivering this high-quality contribution to the community. Open-source fusion modelling just got a big boost!
Paper:
pubs.aip.org/aip/pop/arti...
Paper:
pubs.aip.org/aip/pop/arti...
FreeGSNKE is the UK Fusion Computing Lab's answer to this challenge!
↔️ Fully benchmarked against existing codes
🦾 Robust solvers
🖥️ Modern coding practices
📖 Excellent documentation and tutorials
🌐 Fully open source
github.com/FusionComput...
🧵2/3
↔️ Fully benchmarked against existing codes
🦾 Robust solvers
🖥️ Modern coding practices
📖 Excellent documentation and tutorials
🌐 Fully open source
github.com/FusionComput...
🧵2/3
GitHub - FusionComputingLab/freegsnke: FreeGSNKE: A Python code for evolutive free-boundary tokamak plasma equilibrium simulations
FreeGSNKE: A Python code for evolutive free-boundary tokamak plasma equilibrium simulations - FusionComputingLab/freegsnke
github.com
January 16, 2025 at 11:46 AM
FreeGSNKE is the UK Fusion Computing Lab's answer to this challenge!
↔️ Fully benchmarked against existing codes
🦾 Robust solvers
🖥️ Modern coding practices
📖 Excellent documentation and tutorials
🌐 Fully open source
github.com/FusionComput...
🧵2/3
↔️ Fully benchmarked against existing codes
🦾 Robust solvers
🖥️ Modern coding practices
📖 Excellent documentation and tutorials
🌐 Fully open source
github.com/FusionComput...
🧵2/3
📝 In our paper, we back up our empirical findings with upper and lower regret bounds.
Check it out! arxiv.org/abs/2410.16972
#NeurIPS2024 #research #ml
🧵 4/4
Check it out! arxiv.org/abs/2410.16972
#NeurIPS2024 #research #ml
🧵 4/4
Sample-efficient Bayesian Optimisation Using Known Invariances
Bayesian optimisation (BO) is a powerful framework for global optimisation of costly functions, using predictions from Gaussian process models (GPs). In this work, we apply BO to functions that exhibi...
arxiv.org
November 21, 2024 at 12:14 PM
📝 In our paper, we back up our empirical findings with upper and lower regret bounds.
Check it out! arxiv.org/abs/2410.16972
#NeurIPS2024 #research #ml
🧵 4/4
Check it out! arxiv.org/abs/2410.16972
#NeurIPS2024 #research #ml
🧵 4/4
⚡ Invariant BO has a whole host of applications. We tackle a difficult design task from nuclear fusion: designing a heating system for STEP, the UK's flagship next-gen fusion reactor.
🧵 3/4
#STEPtoFusion #fusionenergy
🧵 3/4
#STEPtoFusion #fusionenergy
November 21, 2024 at 12:14 PM
⚡ Invariant BO has a whole host of applications. We tackle a difficult design task from nuclear fusion: designing a heating system for STEP, the UK's flagship next-gen fusion reactor.
🧵 3/4
#STEPtoFusion #fusionenergy
🧵 3/4
#STEPtoFusion #fusionenergy
⬆️ Using an invariant kernel massively boosts sample efficiency (red line).
For a low-cost approximation, you can use a *subset* of symmetries without sacrificing improved performance (yellow + green lines).
🧵 2/4
For a low-cost approximation, you can use a *subset* of symmetries without sacrificing improved performance (yellow + green lines).
🧵 2/4
November 21, 2024 at 12:14 PM
⬆️ Using an invariant kernel massively boosts sample efficiency (red line).
For a low-cost approximation, you can use a *subset* of symmetries without sacrificing improved performance (yellow + green lines).
🧵 2/4
For a low-cost approximation, you can use a *subset* of symmetries without sacrificing improved performance (yellow + green lines).
🧵 2/4