Fetching from the wire…
Research2026-08-12 · source-backed
Sampled softmax cuts the O(nK) memory of full-vocabulary classification to O(nk), but for fixed budget B = n·k it's been unclear whether to buy batch or negatives (arXiv 2608.11061). Analyzing convergence under standard smoothness and variance assumptions, the fastest convergence comes from n ~ B, k ~ 1. Confirmed on synthetic experiments and four real sequential recommendation benchmarks including MovieLens-20M. Rare thing: a paper that ends in a rule you can apply without reading it twice.
Each link below shares sources, entities, or timing with this story.
Shared entity: Under / Same source domain / Shared topic / Earlier coverage
Both cover Under; reported by the same outlet (arxiv.org); overlapping topics (benchmark, under).
Both cover Under; reported by the same outlet (arxiv.org); overlapping topics (assumption, benchmark).
Both cover Under; reported by the same outlet (arxiv.org); overlapping topics (benchmark, memory).
Both cover Under; reported by the same outlet (arxiv.org); overlapping topics (fixed, under).
Shared entity: Under / Same source domain / Earlier coverage / Tension
Both cover Under; reported by the same outlet (arxiv.org); earlier Under coverage from 2026-08-07.
Both cover Under; reported by the same outlet (arxiv.org); earlier Under coverage from 2026-08-05.
Shared entity: Rare / Same source domain / Earlier coverage / Tension
Both cover Rare; reported by the same outlet (arxiv.org); earlier Rare coverage from 2026-07-16.
Shared entity: Under / Same source domain / Earlier coverage
Both cover Under; reported by the same outlet (arxiv.org); earlier Under coverage from 2026-08-05.