🧑‍🔬 Peter D. Bailis

🏛️ Affiliations

🎓Stanford UniversityStanford · United States2016–2025 · 70 papersEmployment🎓University of California, BerkeleyBerkeley · United States2011–2015 · 22 papersEducation🏢Sisu DataSan Francisco · United States2021–2022 · 3 papers🏢MicrosoftRedmond · United States2018–2020 · 3 papers🎓Harvard UniversityCambridge · United States2010–2011 · 2 papers

🏛️Harvard CollegeCambridge · United StatesEducation

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Break the Sequential Dependency of LLM Inference Using Lookahead Decoding (2024 · 114 citations)
   Generating text with LLMs one token at a time is slow. Each step is limited by memory bandwidth, so most of the GPU's compute sits idle. Speculative decoding helps, but it needs a draft model, which is hard to train and often fails to transfer across base models or datasets. The authors propose Lookahead Decoding…
2. Online Speculative Decoding (2023 · 65 citations)
   Speculative decoding speeds up LLM inference by having a small draft model propose tokens that a large target model checks in parallel.

All works

27 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Bolt-on causal consistency ↗Proceedings - ACM-SIGMOD International Conference on Management of Data · no summary yetPeter D. Bailis et al.2013 · 215 citations
2. Highly available transactions ↗Proceedings of the VLDB Endowment · no summary yetPeter D. Bailis et al.2013 · 204 citations
3. Coordination avoidance in database systems ↗Proceedings of the VLDB Endowment · no summary yetPeter D. Bailis et al.2014 · 191 citations
4. Probabilistically bounded staleness for practical partial quorums ↗Proceedings of the VLDB Endowment · no summary yetPeter D. Bailis et al.2012 · 185 citations
5. Selection via Proxy: Efficient Data Selection for Deep Learning ↗arXiv (Cornell University) · no summary yetCody Coleman et al.2019 · 148 citations
6. Break the Sequential Dependency of LLM Inference Using Lookahead DecodingarXiv:2402.02057Yichao Fu, Peter Bailis, Ion Stoica, et al.2024 · 114 citations
7. Scalable atomic visibility with RAMP transactions ↗Proceedings - ACM-SIGMOD International Conference on Management of Data · no summary yetPeter D. Bailis et al.2014 · 95 citations
8. The potential dangers of causal consistency and an explicit solution ↗ACM Symposium on Cloud Computing (SoCC) · no summary yetPeter D. Bailis et al.2012 · 79 citations
9. Feral Concurrency Control ↗Proceedings - ACM-SIGMOD International Conference on Management of Data · no summary yetPeter D. Bailis et al.2015 · 72 citations
10. Online Speculative DecodingarXiv:2310.07177Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, et al.2023 · 65 citations
11. Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems ↗arXiv (Cornell University) · no summary yetLingjiao Chen et al.2024 · 46 citations
12. Quantifying eventual consistency with PBS ↗The VLDB Journal · no summary yetPeter D. Bailis et al.2013 · 46 citations
13. Scalable Atomic Visibility with RAMP Transactions ↗ACM Transactions on Database Systems · no summary yetPeter D. Bailis et al.2016 · 39 citations
14. Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems ↗neural information processing systems · no summary yetLingjiao Chen et al.2024 · 27 citations
15. MLSys: The New Frontier of Machine Learning Systems ↗arXiv (Cornell University) · no summary yetAlexander Ratner et al.2019 · 19 citations
16. TAOBench ↗Proceedings of the VLDB Endowment · no summary yetAudrey Cheng et al.2022 · 18 citations
17. HAT, not CAP: towards highly available transactions ↗no summary yetPeter D. Bailis et al.2013 · 18 citations
18. RAMP-TAO ↗Proceedings of the VLDB Endowment · no summary yetAudrey Cheng et al.2021 · 14 citations
19. Towards Optimal Transaction Scheduling ↗Proceedings of the VLDB Endowment · no summary yetAudrey Cheng et al.2024 · 12 citations
20. Asynchronous Complex Analytics in a Distributed Dataflow Architecture ↗arXiv (Cornell University) · no summary yetJoseph E. Gonzalez et al.2015 · 10 citations
21. Highly Available Transactions: Virtues and Limitations (Extended Version) ↗arXiv (Cornell University) · no summary yetPeter D. Bailis et al.2013 · 10 citations
22. Optimizing Model Selection for Compound AI Systems ↗arXiv (Cornell University) · no summary yetLingjiao Chen et al.2025 · 9 citations
23. PBS at work ↗Proceedings - ACM-SIGMOD International Conference on Management of Data · no summary yetPeter D. Bailis et al.2013 · 9 citations
24. Coordination-Avoiding Database Systems. ↗arXiv (Cornell University) · no summary yetPeter D. Bailis et al.2014 · 3 citations
25. Select Via Proxy: Efficient Data Selection For Training Deep Networks ↗no summary yetCody Coleman et al.2018 · 2 citations

See all 27 works by Peter D. Bailis →

🤝 Co-authors here

5 co-authors with a page, the most papers together first.

• Hao Zhang ×2
• Ion Gabriel Stoica ×2
• Alvin Cheung
• Yichao Fu
• Zhijie Deng

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Proceedings of the VLDB Endowment ×7
• Proceedings - ACM-SIGMOD International Conference on Management of Data ×4
• ACM Symposium on Cloud Computing (SoCC)
• ACM Transactions on Database Systems
• The VLDB Journal
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 310 times (of the 149,439 papers whose bibliographies we read); 58 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/peter-d-bailis/