A cheap test beforean expensive one
GPU time on a shared cluster is scarce, so I built a way to rank ideas before training any of them.
Training a temporal model is expensive, and the GPU grid at Idiap is shared — a wasteful experiment is a cost to the whole group. That constraint shaped the method: wherever possible, rank ideas before committing compute to them.
The Temporal Separability Benchmark reuses the same lightweight LDA probe from the phase work as a fast scoring instrument — so competing configurations can be compared in minutes, not in full training runs.
Three questions, settled cheaply.
Yes — temporal structure exists
Diminishing returns
Keep RETFound-Green
The PCA study that was worth running anyway.
A separate controlled study asked whether compressing the frozen embeddings with PCA before the recurrent model would help. It did not — no improvement in macro-ROC-AUC or average precision.
A negative result is not a wasted one. It removed an attractive but non-beneficial branch from the design space, kept the implementation simpler, and is documented so the next researcher does not have to re-run it.