Approximate Top-K Algorithms

  • Last Updated 14 June, 2026
  • by David Spuler, Ph.D.

Research on Approximate Top-K Algorithms

Research papers include:

  • Yashas Samaga, Varun Yerram, Spandana Raj Babbula, Prateek Jain, Praneeth Netrapalli, 5 Jun 2025 (v2), Faster Approx. Top-K: Harnessing the Full Power of Two Stages, https://arxiv.org/abs/2506.04165
  • Felix Chern, Blake Hechtman, Andy Davis, Ruiqi Guo, David Majnemer, Sanjiv Kumar, 30 Jun 2022 (v2), TPU-KNN: K Nearest Neighbor Search at Peak FLOP/s, https://arxiv.org/abs/2206.14286
  • Patt-Shamir, B., Shafrir, A. Approximate distributed top-k queries. Distrib. Comput. 21, 1–22 (2008). https://doi.org/10.1007/s00446-008-0055-3 https://link.springer.com/article/10.1007/s00446-008-0055-3
  • Oscar Key, Luka Ribar, Alberto Cattaneo, Luke Hudlass-Galley, Douglas Orr, 5 Dec 2024, Approximate Top- for Increased Parallelism, https://arxiv.org/abs/2412.04358
  • Long Cheng, Ritchie Zhao, Timmy Liu, Mindy Li, Xianjie Qiao, Kefeng Duan, Yu-Jung Chen, Xiaoming Chen, Bita Darvish Rouhani, June Yang, 24 Apr 2026, Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation, https://arxiv.org/abs/2604.22312 (Faster computation of top-k selection in DSA.)
  • Yashas Samaga B L, Varun Yerram, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli, 14 Feb 2024, HiRE: High Recall Approximate Top- Estimation for Efficient LLM Inference, https://arxiv.org/abs/2402.09360

More AI Research Topics

Read more about: