← Back to writing
Neural surrogates for physics-based inverse problems
When the forward model is slow, the prior is cheap, and the data is small.
Physics-based inverse problems live in a strange corner of ML. The forward model is expensive but exact; the dataset is small but informative; the prior is cheap because you already know how the system works. A neural surrogate lets you keep the physics and still run the inverse loop in real time.
Notes in progress — full write-up coming soon.