Research · first-author · under review at NeurIPS 2026
PTNO: Positive Transport Neural Operators
Neural-operator surrogates for Monte Carlo particle transport, trained on cheap, noisy MC labels across 1M+ configurations. Keeping supervision in linear space behind a positivity-preserving head sidesteps the Jensen bias of log-transformed noisy labels, so the model predicts fields spanning 9–11 orders of magnitude, ends up more accurate than its own training labels, and runs inference up to ~10⁶× faster than converged Monte Carlo. Work with Prof. Anima Anandkumar's lab at Caltech.
- PyTorch
- Neural operators
- CUDA / NVIDIA Warp
- Slurm