Drew Prinster @ ICML
@DrewPrinster
Trustworthy AI/ML in healthcare & high-stakes apps | My job is (mostly) error bars 🫡 (eg, conformal prediction) | CS PhD at Johns Hopkins. Prev at Yale. he/him
Paper 🧵! w/ @samuel_stanton_ @anqi_liu33 @suchisaria #ICML2024 arxiv.org/abs/2405.06627 We study 2 Qs: 1) Can AI uncertainty quant. via #ConformalPrediction extend to any data distribution? 2) Are there practical CP algorithms for AI/ML agents 🤖w/ feedback-loop data shifts? 1/
Best read as a reasoned call to action, not a question. And we will need vivid terms for where we are going — oligarchy and fascism — as well as what we are seeking — freedom and equality. nytimes.com/2025/05/08/opi…
Where's Waldo? 🧐 Maybe you'll find him on our poster, but you can definitely find me at #ICML2025! - Invited Talk: Tue (7/15) Multi-Agent Systems in Ambient Settings Social (~7:45pm) - Poster: Thu (7/17) morning (11-1:30pm), East Exhibit Hall, E-1912 icml.cc/virtual/2025/p…
AI monitoring is key to responsible deployment. Our #ICML2025 paper develops approaches for 3 main goals: 1) *Adapting* to mild data shifts 2) *Quickly Detecting* harmful shifts 3) *Diagnosing* cause of degradation 🧵w/ @xinghan0 @anqi_liu33 @suchisaria arxiv.org/abs/2505.04608
I’m at #ICML2025 this week presenting my work on multiaccuracy and multicalibration with proxy sensitive attributes. If you are interested, please come by poster E-1101 on Tuesday at 4:30 pm PST to learn more! @Jere_je_je @PaulYiMD icml.cc/virtual/2025/p…
I am not going to make this ICML but @DrewPrinster will be there! Check out our recent work on online AI monitoring under a non-stationary environment.
& “WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales” by @DrewPrinster, @xinghan0, @anqi_liu33, & @suchisaria proposes a weighted generalization of conformal test martingales: arxiv.org/abs/2505.04608 (5/5)
🚨With an awesome group of collaborators from health system & federal agencies, @Jean_J_Feng and I are embarking on an ambitious multi-year project to develop tools for monitoring & updating clinical AI algorithms, with the aim of informing how we accelerate & scale responsible…
For #WorldHealthDay, a new study by Hopkins researchers including @suchisaria, @DrewPrinster, & more finds that doctors’ diagnostic performance and trust in #AI advice depends on just how exactly the AI assistant explains itself. Learn more: cs.jhu.edu/news/explain-y…