top-k-selection

Prof-K is a probabilistic one-pass filtering algorithm for fast, scalable top-k selection with correctness guarantees, achieving 1.5x–10x speedups over PyTorch topk and RadiK, especially in large-scale small-k regimes.

LaPrune introduces a differentiable sparse-selection layer that independently controls budget and mask hardness at million scale, using a LapSum barrier and normalized second-moment constraint to approximate hard top-k selection while preserving selected mass.