🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to share that our paper "Self-Calibrating Conformal Prediction" with Ahmed Alaa is accepted at #NeurIPS2024! 🚀 We combine model calibration and prediction intervals by integrating Venn-Abers into conformal prediction. #conformal #calibration arxiv.org/abs/2402.07307

Automatic doubly robust inference for linear functionals via calibrated debiased machine learning. arxiv.org/abs/2411.02771

Very excited about this paper on calibration and debiased machine learning being released! Details coming soon!

Join us on Nov 13 for another exciting talk in our CTML Seminar Series! Gilmer Valdes’ talk “Unleashing Sparse Regularization: Equation for Setting Regularization Strength to Achieve Targeted Compression in CNNs and Transformers” will take place at 11AM at BWW, 5th Fl, Rm 5401.

If you are doing causal inference with machine learning, calibrate your nuisances! More details to come…

A rare & exciting cross-disciplinary cross-sector 4y fully-funded PhD opportunity: Targeted Causal Inference for Real World Evidence in Healthcare, with academia (me, Sjoerd Beentjes,Mark van der Laan Kenneth Baillie), the National Institute for Health & Care Excellence and industry.

Join us on Nov 20 for another outstanding talk in our Fall 2024 CTML Seminar Series! Stathis Gennatas’ talk "Theory, Education, Application, Deployment: Designing Software to Bring Advanced Health Data Science to All" will take place at 11:00AM at BWW, 5th Floor, Rm 5401.

FIORD 2024 drew 60 experts from regulatory, government, pharmaceutical, academic, and industry sectors, creating a dynamic platform for collaboration and innovation. 19 speakers & 13 panelists contributed unique insights and expertise that broadened the forum’s scope and impact!

Excited to present "Self-Calibrating Conformal Prediction" at #NeurIPS2024 this afternoon! Join me at the poster session to learn how combining model calibration with predictive inference gives calibrated point predictions and conditionally valid prediction intervals. #conformal

In Poster Session 4 (4:30 pm - 7:30 pm PST), Lars van der Laan will present our work on combining model calibration and prediction intervals by integrating Venn-Abers into conformal prediction.

Excited to share our work on Double RL and long-term causal inference! This project grew out of my internship at Netflix last summer.

Friendly reminder: The abstract and full paper submissions for the International Conference on Machine Learning (ICML) is due next week for their 2025 conference in Vancouver, Canada from July 13-19. Click the link in our bio to apply today!

Thrilled to share our new paper! We introduce a generalized autoDML framework for smooth functionals in general M-estimation problems, significantly broadening the scope of problems where automatic debiasing can be applied! Link: arxiv.org/pdf/2501.11868

Join us next week February 5th to continue our CTML Seminar Series! Kaiwen Hou will give his talk on "Hierarchical Approximation of Universal Least Favorable Paths for Improved Efficiency." This talk will take place at 12:00PM at Berkeley Way West, 5th Floor, Room 5401.

Big news! CTML is now on Bluesky! 🚀 Follow and join us on Bluesky at berkeleyctml.bsky.social. We look forward to expanding our network and sharing our latest research, events, and insights with you! 💡 #BerkeleyCTML #BlueSky

We have two papers accepted at #ICML2025! An oral on construct validity of medical LLM benchmarks and a poster on generalized Venn-Abers calibration. See you in Vancouver 🇨🇦!

🚨

Excited to share that our paper on uncertainty-aware model calibration using generalized Venn–Abers methods was accepted to #ICML2025! We show that Vovk’s Venn–Abers calibration and conformal prediction are both special cases of a unified framework.

Great to see our work with Maya Petersen, Emre Kıcıman, Chris Holmes and Mark van der Laan featured by Microsoft Research!

CTML VSR alum Carlos Meixide and CTML co-director Mark van der Laan present a new approach to causal inference. The new paper challenges the traditional assumption-based identification to what can be learned directly from observed data using implied interventions. Link in bio!🔗