PeopleofSuperintelligence

Researcher

Alex Wang

Also known as Alex L. Wang

Alex Wang is an optimization researcher whose work extends classical optimization theory to problems inspired by data science. He earned a B.S. in computer science and mathematics at Northwestern University and completed a computer science Ph.D. at Carnegie Mellon in 2022 under Fatma Kılınç-Karzan; he then worked on optimization for machine learning at CWI. His 2022 paper on the Stackelberg prediction game won an ICML Outstanding Paper Award, and in 2023 he coauthored long-step gradient descent work that established an accelerated rate. With Benjamin Grimmer and Kevin Shu, he also developed the Subgame Perfect Gradient Method in 2024; as of October 2026 he is an assistant professor in Purdue’s Quantitative Methods Group and co-organizes its seminar.

Links
Google Scholar

Timeline

  1. 2021

    The INFORMS student paper prize

    In 2021, he wins the INFORMS Optimization Society Student Paper Prize for “On the Tightness of SDP Relaxations of QCQPs,” coauthored with Fatma Kılınç-Karzan. The paper examines semidefinite programming relaxations of general quadratically constrained quadratic programs.

  2. By 2022

    Computer science and mathematics degrees

    He earns a B.S. in computer science and mathematics at Northwestern University, then completes a Ph.D. in computer science at Carnegie Mellon University in 2022 under Fatma Kılınç-Karzan.

  3. 2022

    The Stackelberg prediction game award

    He coauthors “Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation” with Jiali Wang, Wen Huang, Rujun Jiang and Xudong Li; ICML gives the paper an Outstanding Paper Award in 2022. The Stackelberg prediction game models strategic interaction between a learner and an attacker, and numerical results on synthetic and real-world datasets indicate that its reformulation can solve the problem orders of magnitude faster than the state of the art.

  4. 2022

    Postdoc at CWI

    In fall 2022, he is a postdoctoral researcher at Centrum Wiskunde & Informatica in the Optimization for and with Machine Learning project, supervised by Monique Laurent.

  5. September 2023

    Long steps for gradient descent

    In September 2023, he posts “Accelerated Gradient Descent via Long Steps” with Benjamin Grimmer and Kevin Shu. The work establishes gradient descent’s first accelerated convergence rate in smooth convex minimization, O(1/T^1.0564).

  6. December 2024–January 2026

    A subgame perfect gradient method

    In December 2024, he posts “Beyond Minimax Optimality: A Subgame Perfect Gradient Method” with Benjamin Grimmer and Kevin Shu. The method refines the Optimized Gradient Method to use the full history of first-order information, reaches dynamic optimality in the sense of a subgame perfect equilibrium, and is published in Mathematical Programming. In January 2026, Purdue’s Daniels School features the method and quotes Wang.

  7. 2025

    Stronger stepsize analysis

    In 2025, he coauthors “Accelerated Objective Gap and Gradient Norm Convergence for Gradient Descent via Long Steps” with Benjamin Grimmer and Kevin Shu; it appears in the INFORMS Journal on Optimization. The paper significantly shortens and strengthens the analysis for stepsize sequences in their 2023 technical report “Accelerated Gradient Descent via Long Steps.”

  8. As of October 2026

    Assistant professor at Purdue

    As of October 2026, he is an assistant professor in the Quantitative Methods Group at Purdue’s Daniels School of Business. He and Billy Jin organize the Quantitative Methods Seminar, and his research extends classical optimization theory toward data science, with topics including semidefinite programming, first-order methods and nonconvex quadratic programming.

Career

  1. NowPurdue UniversityAssistant professor
  2. From 2022NWO-IPostdoctoral researcher

Education

  1. 2022Carnegie Mellon UniversityPh.D. in computer science
  2. Northwestern UniversityB.S.

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 Alex Wang. 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 Purdue University. 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. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Purdue University. 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.
  4. Google has the highest combined h-index among AI organizationsIncludes Purdue University. 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.

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 Alex Wang yet. Send us a free-licensed photo.

  1. Tepper Faculty Accolades - Tepper School of Business - Carnegie Mellon University cmu.edu. Checked 22 October 2026.
  2. Directory Details - Purdue Business business.purdue.edu. Checked 22 October 2026.
  3. Alex L. Wang a-l-wang.com. Checked 22 October 2026.
  4. Congratulations to the #ICML2022 outstanding paper award winners - AIhub aihub.org. Checked 22 October 2026.
  5. ICML 2022 Awards icml.cc. Checked 22 October 2026.
  6. Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation (arXiv:2206.02991) arxiv.org. Checked 22 October 2026.
  7. Accelerated Gradient Descent via Long Steps (arXiv:2309.09961) arxiv.org. Checked 22 October 2026.
  8. Beyond Minimax Optimality: A Subgame Perfect Gradient Method (arXiv:2412.06731) arxiv.org. Checked 22 October 2026.
  9. Reframe the Problem, Find A New ‘Best’ Algorithm - Purdue Business business.purdue.edu. Checked 22 October 2026.
  10. Alex L. Wang - publications a-l-wang.com. Checked 22 October 2026.
  11. Quantitative Methods Faculty - Purdue Business business.purdue.edu. Checked 22 October 2026.