I'm an associate professor in the Stanford AI Lab (SAIL) affiliated with DAWN and the Statistical Machine Learning Group (bio). Our lab works on the foundations of the next generation of machine-learned systems. While we're very proud of our research ideas and their impact, the lab's real goal is to help amazing students become professors, entrepreneurs, and researchers. With my students and collaborators, I've been fortunate enough to cofound projects including Lattice, now part of Apple, inductiv, SambaNova, and Snorkel. The honor that still doesn't feel real is the MacArthur Fellowship.
On the machine learning side, I am fascinated by how we can learn from increasingly weak forms of supervision and the mathematical foundations of such techniques. On the systems side, I am broadly interested in how machine learning is changing how we build software and hardware. I'm particularly excited when we can blend ML and Systems, e.g,. Snorkel. My MLSys 20 keynote talk (pdf|pptx) has an overview of our recent work. As for future directions, the lab wrote up some content about their take on our past and future directions hosted on new group website
- Students and Postdocs described their view on Software 2.0 and what's next
- Upcoming talks: Dagstuhl on ML meets Software Engineering, SysML (Keynote), OPsML@SysML, WWW BIG, WWW IDS, DAC Sky Talk, Duke
- Snorkel is in a new location Snorkel.org. Crazily enough, you've probably used a system that has a Snorkel-powered or Snorkel-inspired component in the last few hours (thanks to collaborations with Google ads, the folks at Gmail, Apple, and many more). Excited for all the great collaborations!
- In ICLR2020. CRCs coming!
- Hongyang and Sen describe theory that helps tell us when multitask learning works--and when it doesn't!
- Tri et al. describe Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps, and they show they can learn hand-tuned features in speech pipelines--from scratch! Spotlight
- In CIDR20, paper about our Overton work at Apple including zero-code deep learning, weak supervision, and data slicing (an idea in NeurIPS 19 below).
- NeurIPS19. Preprints, blog posts, and code releases coming soon!
- Avner, Jian, and Tri discuss how compression of word embeddings changes downstream performance of ML models with a mix of theory and empirical study. spotlight.
- Fred and Paroma led work about how to do weak supervision for sequential data at multiple scales, e.g., for learning in video. Available in Snorkel. Also used in the below Nature Comms paper.
- Vincent, Sen, and Alex describe their work Slice-based Learning: A programming model for residual learning on critical slices. Available in Snorkel. blog.
- Ines, Rex, and Jure describe Hyperbolic Graph Convolutional Neural Networks. This builds on our recent interest to understand when it helps to incorporate (non-Euclidean) geometry into state-of-the-art embedding methods.
- Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging by Dr. Luke Oakden-Rayden and Jared with blog in ML4H.
- A bunch of great collaborations in nature family journals and clinical journals
- In NPJ Digital Medicine, Khaled leads applying weak supervision to EEG for efficient seizure detection.
- In NPJ Digital Med., Alison Callahan and Jason A Fries led an amazing effort to apply weak supervision in device surveillance in health records or here.
- In Nature Comms, Weak supervision for Cardiac MRI videos for rare aoritc valve disorders
- In Nature Comms, the world's largest machine read GWASKB--both with help from Snorkel's ideas.
- In Radiology Jan 19, Jared's paper about using deep learning in image triage: at what training set sizes do modern methods provide utility in radiology? This is collaboration with great folks in the medical school!
A messy, incomplete log of old updates is here.