PeopleofSuperintelligence

Researcher

Rajiv Khanna

Rajiv Khanna is a machine learning researcher who studies why learning algorithms behave as they do, with work on optimization, learning theory, interpretability and machine unlearning. After an MTech at IIT Bombay in 2008 and a research engineer post at Yahoo Labs Bangalore from 2008 to 2012, he earned a PhD in electrical and computer engineering at the University of Texas at Austin in 2018. A postdoc at UC Berkeley followed from 2019 to 2021, with Michael Mahoney as mentor, and a paper he coauthored there with Michal Derezinski and Mahoney on column subset selection and the Nyström method won a NeurIPS 2020 Best Paper Award. He joined Purdue's Department of Computer Science in 2022 and received an NSF CAREER Award in 2026 for a project titled "Algorithmic Advances in Structure-aware Learning". He is an assistant professor of computer science at Purdue.

Badges

Timeline

  1. 2008–2012

    Research engineer at Yahoo Labs

    He completes an MTech in computer science at IIT Bombay in 2008 and joins Yahoo Labs Bangalore as a research engineer. Until 2012, his work there covers web-scale click prediction, recommendation systems and modeling skewed data.

  2. 2018

    PhD and a Simons fellowship

    He earns a PhD in electrical and computer engineering at the University of Texas at Austin in 2018. In fall 2018, he holds a Simons-Berkeley Research Fellowship in the Foundations of Data Science program at the Simons Institute at UC Berkeley.

  3. 2019–2021

    Postdoc with Michael Mahoney

    From spring 2019 to spring 2021, he is a postdoctoral researcher at UC Berkeley's Foundations of Data Analytics Institute, in the Department of Statistics with Michael Mahoney as mentor.

  4. 2020

    A NeurIPS Best Paper Award

    With Michal Derezinski and Michael Mahoney, he coauthors "Improved Guarantees and a Multiple-Descent Curve for Column Subset Selection and the Nyström Method", one of three papers that win a NeurIPS 2020 Best Paper Award. The paper uses spectral properties of the data matrix to sharpen approximation guarantees and shows that the approximation factor can rise and fall as the subset size k grows, a pattern the authors call a multiple-descent curve.

  5. 2021–2022

    Joining Purdue Computer Science

    In fall 2021, he is a visiting researcher at Google Research. He joins Purdue University's Department of Computer Science as an assistant professor for the spring 2022 semester, part of a 2021 hiring effort that brings in eight new faculty, with research on optimization, theory and interpretability, including the theory and practice of greedy algorithms.

  6. 2023

    AnalytiXIN research fellow

    In November 2023, Purdue's Office of Research names him one of nine faculty research fellows in AnalytiXIN, an academic-industry initiative based in Indianapolis. Purdue describes his research as machine learning, including optimization, theory and interpretability.

  7. 2026

    An NSF CAREER Award

    In 2026, he receives a five-year NSF CAREER Award of $357,921 for "Algorithmic Advances in Structure-aware Learning", a project on how the structure of data shapes what machine learning systems learn. It produces mathematical theory, practical algorithms, experimental benchmarks, open-source tools and instructional materials.

  8. As of October 2026

    Assistant professor at Purdue

    He is an assistant professor of computer science at Purdue, and his research spans optimization, learning theory, interpretability and privacy. He is affiliated with Purdue's Center for Education and Research in Information Assurance and Security (CERIAS), where he is principal investigator of a machine unlearning project. His group studies what trained models remember, which data matters and how people and AI can work together.

Career

  1. Since 2022Purdue UniversityAssistant Professor
  2. 2021Google ResearchVisiting Researcher
  3. 2019–2021University of California, BerkeleyPostdoctoral Researcher
  4. 2008–2012YahooResearch Engineer

Education

  1. 2018University of Texas at AustinPhD in Electrical and Computer Engineering
  2. 2008IIT BombayMTech in 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 Rajiv Khanna. 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. Google had the most people shaping AI every year from 2014 to 2025Includes Google. 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.
  3. Google has the highest combined h-index among AI organizationsIncludes Google. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  4. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Google. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.

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 Rajiv Khanna yet. Send us a free-licensed photo.

  1. Rajiv Khanna - CERIAS - Purdue University cerias.purdue.edu. Checked 22 October 2026.
  2. Assistant Professor Rajiv Khanna is newest faculty member to join Purdue Computer Science cs.purdue.edu. Checked 22 October 2026.
  3. Announcing the NeurIPS 2020 award recipients blog.neurips.cc. Checked 22 October 2026.
  4. Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nystrom method proceedings.neurips.cc. Checked 22 October 2026.
  5. Rajiv Khanna - Department of Computer Science - Purdue University cs.purdue.edu. Checked 22 October 2026.
  6. Khanna and Zikas named as research fellows to collaborate, innovate with AnalytiXIN cs.purdue.edu. Checked 22 October 2026.
  7. Khanna earns NSF CAREER Award cs.purdue.edu. Checked 22 October 2026.
  8. 15 faculty chosen for NSF CAREER awards purdue.edu. Checked 22 October 2026.
  9. Rajiv Khanna | Machine Learning Research at Purdue rjvak7.github.io. Checked 22 October 2026.
  10. CERIAS: Machine Unlearning cerias.purdue.edu. Checked 22 October 2026.