PeopleofSuperintelligence

Researcher

Alexander Rakhlin

Also known as Sasha Rakhlin

Alexander Rakhlin is a machine learning researcher whose work develops theory and algorithms for online prediction and interactive decision making. He earned bachelor's degrees in mathematics and computer science from Cornell and a PhD at MIT in 2006. After a postdoc in UC Berkeley's EECS department, he served as an associate professor in Penn's Department of Statistics and co-director of the Penn Research in Machine Learning center; he was a visiting professor at MIT from 2016 and joined its Department of Brain and Cognitive Sciences and IDSS in 2018. With Karthik Sridharan, he published a 2013 paper on online learning with predictable sequences; with Dylan Foster, he co-wrote 2023 lecture notes on reinforcement learning and interactive decision making, and presented related work at an EPFL seminar in April 2025. In 2026, a paper with Fan Chen, Sinho Chewi, and Constantinos Daskalakis on high-accuracy diffusion sampling won an ICML Outstanding Paper Award; as of October 2026, he directs MIT's Statistics and Data Science Center and is a professor of brain and cognitive sciences and Distinguished Professor in Data, Systems, and Society.

Links
Website

Timeline

  1. 2006

    Cornell degrees and an MIT PhD

    He earns bachelor's degrees in mathematics and computer science from Cornell University and a PhD at MIT in 2006.

  2. 2013

    Online learning with predictable sequences

    In 2013, he and Karthik Sridharan present methods for online linear optimization that take advantage of predictable sequences, with tighter bounds when the data follow a known predictable process.

  3. 2016–2018

    Visiting professor at MIT

    From 2016, he serves as a visiting professor at MIT's Statistics and Data Science Center, then formally joins MIT's Department of Brain and Cognitive Sciences and IDSS in 2018.

  4. By 2018

    Berkeley postdoc and Penn faculty

    After a postdoc in UC Berkeley's EECS department, he serves as an associate professor in Penn's Department of Statistics and co-director of the Penn Research in Machine Learning center by 2018.

  5. 2023

    Foundations of reinforcement learning

    With Dylan J. Foster, he coauthors the monograph Foundations of Reinforcement Learning and Interactive Decision Making in 2023. It gives a statistical framework from multi-armed and contextual bandits through structured bandits to reinforcement learning with function approximation.

  6. April 2025

    An EPFL AI seminar

    At an EPFL AI Center seminar in April 2025, he presents a framework for interactive decision making that covers multi-armed and contextual bandits, structured bandits, and reinforcement learning.

  7. 2026

    A diffusion sampling award

    His paper with Fan Chen, Sinho Chewi, and Constantinos Daskalakis, High-Accuracy Sampling for Diffusion Models and Log-Concave Distributions, wins the ICML 2026 Outstanding Paper Award. It uses first-order rejection sampling to reach ε-error in polylog(1/ε) steps.

  8. As of October 2026

    MIT Statistics Center director

    As of October 2026, he directs MIT's Statistics and Data Science Center, is a professor of brain and cognitive sciences, and holds the Distinguished Professorship in Data, Systems, and Society. His research develops theoretical and algorithmic tools for online prediction.

Career

  1. Since 2016Massachusetts Institute of TechnologyVisiting Professor, Professor
  2. Until 2018University of PennsylvaniaAssociate Professor
  3. University of California, BerkeleyPostdoc

Education

  1. 2006Massachusetts Institute of TechnologyPhD
  2. Cornell UniversityBachelor's degrees in mathematics and computer science

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Alexander Rakhlin. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Massachusetts Institute of Technology. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. Google had the most people shaping AI every year from 2014 to 2025Includes Massachusetts Institute of Technology. Our estimates of which organizations employed the most people shaping AI each year from 1955 to 2025, tracing the shift from university labs to companies.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Massachusetts Institute of Technology. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations 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 Alexander Rakhlin yet. Send us a free-licensed photo.

  1. Alexander Rakhlin named director of the MIT Statistics and Data Science Center news.mit.edu. Checked 21 October 2026.
  2. Alexander Rakhlin | Brain and Cognitive Sciences bcs.mit.edu. Checked 21 October 2026.
  3. Online Learning with Predictable Sequences proceedings.mlr.press. Checked 21 October 2026.
  4. [2312.16730] Foundations of Reinforcement Learning and Interactive Decision Making arxiv.org. Checked 21 October 2026.
  5. FLAIR x AI Center Seminar - AI Fundamentals series - Prof. Alexander Rakhlin memento.epfl.ch. Checked 21 October 2026.
  6. Announcing the ICML 2026 Awards blog.icml.cc. Checked 21 October 2026.
  7. 3 Questions: What is the best path forward for AI in academia? computing.mit.edu. Checked 21 October 2026.