Author here. VarLiNGAM is the reference algorithm for causal discovery in time series. The Python implementation doesn't scale past ~10 variables. I rewrote it from scratch in pure Rust.
Results: 14-50x faster, 3-6x less memory, <1% precision gap vs ground truth. Drop-in replacement via PyO3.
Happy to answer questions about the implementation choices.
1 comment
[ 3.6 ms ] story [ 17.7 ms ] threadResults: 14-50x faster, 3-6x less memory, <1% precision gap vs ground truth. Drop-in replacement via PyO3.
Happy to answer questions about the implementation choices.