
Ameet Talwalkar
Associate Professor · Machine Learning Department — Core Faculty · Carnegie Mellon University
At Prof Rod’s reading desk
Questions to explore
- When is a short training run a useful signal about the final model?
- How should a tuning method allocate a fixed computation budget?
Research interests
Ameet Talwalkar works on machine learning systems and methods, with current interests in AI for science, human-AI interaction and specialized models and agents.
- Machine learning systems
- Hyperparameter optimization
- AI for science
Prof Rod’s reading notes
Start with a paper
JMLR · 2018
Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
Prof Rod’s reading note: Read how successive halving allocates computation among competing configurations. Look for the assumptions behind eliminating a promising model early.
Bring a question of your own
Turn reading into research
Trace one successive-halving bracket. Identify the resource budget, elimination rule and assumption that makes an early score useful.
Courses and teaching
Keep exploring
More at Carnegie Mellon University
Explore the universityImprove this page
Suggest a correction, share a paper to start with, or point readers to a group page or opening.