LabCompass

Qifan Song

Mathematics · Purdue University West Lafayette

OpenAlex
Mid career · publishing since 2004
Statistical Methods and InferenceMarkov Chains and Monte Carlo MethodsGaussian Processes and Bayesian InferenceBayesian Methods and Mixture ModelsExercise and Physiological Responses

Publications

113

Citations

1,052

Est. group size

~14

Recurring co-author estimate

Active years

23

Publishing since 2004

Research summary
AI-generated

Qifan Song works in statistics and machine learning theory, with a focus on Bayesian methods, high-dimensional statistical inference, and the mathematical foundations of neural networks. Recent work examines adversarial robustness of neural networks, generative adversarial networks (GANs), in-context learning in transformers, bandit optimization algorithms, and sparse/matrix estimation problems. The research is largely theoretical, aiming to establish mathematical guarantees for machine learning methods rather than building applied systems.

Bayesian statistics and inferenceStatistical theory for machine learningAdversarial robustness in neural networksHigh-dimensional and sparse estimation (e.g., matrix completion, sparse PCA)Bandit algorithms and online optimization

Publication output grew from a handful of papers in 2017-2019 to a steadier pace of roughly 10-14 papers per year from 2020 onward, suggesting a period of growth followed by sustained, consistent activity.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence
Publications per year over the last 10 years — averaging 9.0/year recently
2017: 3 publications172018: 5 publications182019: 5 publications192020: 14 publications14202021: 10 publications212022: 11 publications222023: 11 publications232024: 11 publications242025: 5 publications252026: 7 publications26
Recent publications
Publishes in
  • arXiv (Cornell University)×37
  • Journal of Applied Physiology×5
  • The FASEB Journal×5
  • Figshare×5
  • Physiology×4
Similar researchers
By research-topic overlap

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile