PeopleofSuperintelligence

Researcher

Christopher De Sa

Also known as Chris De Sa

Christopher De Sa researches asynchronous and low-precision stochastic algorithms for machine learning. He coauthored “Taming the Wild,” which analyzes asynchronous stochastic gradient descent and introduces Buckwild, and shared ICML’s 2016 Best Paper Award for work on asynchronous Gibbs sampling. He graduated from Stanford in 2017, received the NSF CAREER award in 2021, and coauthored a decentralized-training paper that earned an ICML 2021 Outstanding Paper Honorable Mention. By December 2024, he had tenure as a Cornell associate professor and received a DARPA YFA grant for compressed-model fine-tuning; as of October 2026, he leads the Relax ML Lab and coauthors research on language-model memorization.

Works
136
Citations
3,700
h-index
30

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

  1. 2015

    A unified analysis of Hogwild

    He and his coauthors publish “Taming the Wild” in 2015, presenting a martingale-based analysis of stochastic gradient methods that covers asynchronous execution and reduced precision. The paper introduces Buckwild, a lower-precision asynchronous SGD algorithm.

  2. 2016

    An ICML best paper

    With Chris Ré and Kunle Olukotun, he wins ICML’s Best Paper Award in 2016 for a study of asynchronous Gibbs sampling that examines bias and mixing time.

  3. 2017

    Stanford engineering degrees

    He earns B.S., M.A. and Ph.D. degrees in electrical engineering at Stanford. He graduates in 2017 under advisers Kunle Olukotun and Chris Ré.

  4. 2021

    An NSF CAREER award

    He receives the National Science Foundation Faculty Early Career Development (CAREER) Award in 2021.

  5. 2021

    DeTAG and ICML recognition

    In 2021, he and Yucheng Lu receive ICML’s Outstanding Paper Honorable Mention for “Optimal Complexity in Decentralized Training,” which proves a tight iteration-complexity lower bound and proposes DeTAG, a gossip-style decentralized algorithm.

  6. December 2024

    Tenure and a DARPA grant

    By December 2024, he is a tenured associate professor at Cornell and leads the Relax ML Lab. In 2024, he receives a DARPA YFA Grant for “Decentralized Online Parameter-Efficient Fine-Tuning of Compressed Models.”

  7. As of October 2026

    Leading Relax ML Lab

    As of October 2026, he is an associate professor of computer science at Cornell and leads the Relax ML Lab. In October 2026, he coauthors a study that measures memorization across 200 books and 14 open-weight language models.

Career

  1. Since 2017Cornell UniversityAssociate Professor of Computer Science

Education

  1. 2017Stanford UniversityB.S.

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Data Programming: Creating Large Training Sets, Quickly2016 · 384 citationsWith Christopher Ré and Daniel Selsam
  2. Incremental knowledge base construction using DeepDive2015 · Proceedings of the VLDB Endowment · 236 citationsWith Christopher Ré
  3. Improving Neural Network Quantization without Retraining using Outlier Channel Splitting2019 · 231 citations
  4. Soft optoelectronic sensory foams with proprioception2018 · Science Robotics · 202 citations
  5. Representation Tradeoffs for Hyperbolic Embeddings2018 · 184 citationsWith Albert Gu and Christopher Ré

From OpenAlex, as of 19 October 2026.

  1. Stanford University trained or employed 20 of the 89 AI major-prize winners, more than any other universityIncludes Cornell University. Stanford University trained or employed 20 of the 89 AI major-prize winners, more than any other university. We compare doctorate and employment links for major-prize and best-paper winners.
  2. Google has the highest combined h-index among AI organizationsIncludes Cornell University. Our estimates of combined and median h-index at AI organizations, using current affiliations and OpenAlex records.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Cornell University. Our estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.
  4. The company share of AI researchers’ top papers rose from 2% to 32%Includes Cornell University. We estimate where leading AI researchers worked when their most-cited papers appeared. The company share rose from 2% in 1975–1979 to 32% in 2020–2024.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Christopher De Sa yet. Send us a free-licensed photo.

  1. Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms arxiv.org. Checked 19 October 2026.
  2. Chris De Sa cs.cornell.edu. Checked 19 October 2026.
  3. Awards | ICML New York City icml.cc. Checked 19 October 2026.
  4. Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling proceedings.mlr.press. Checked 19 October 2026.
  5. Christopher De Sa | Department of Computer Science | Cornell Bowers cs.cornell.edu. Checked 19 October 2026.
  6. Awards Directory | Cornell Bowers bowers.cornell.edu. Checked 19 October 2026.
  7. ICML 2021 Awards icml.cc. Checked 19 October 2026.
  8. Hazy Alumni Life Updates (2024) · Hazy Research hazyresearch.stanford.edu. Checked 19 October 2026.