Machine Learning: Research directions
- Updated
On this page
Reliable uncertainty under changing conditions
Emerging direction · Research direction; reviewed 2026-11-03
Conformal methods motivate work on uncertainty for structured outputs, time series and distribution shift. Useful guarantees require careful assumptions and calibration. Making a model express uncertainty does not automatically make its uncertainty valid after the environment changes.
A Gentle Introduction to Conformal Prediction — Angelopoulos and Bates / arXiv · Source date: 2021-07-15 · Checked
Efficient learning across heterogeneous devices
Emerging direction · Research direction; reviewed 2026-11-03
Federated learning addresses the tension between locally held data and shared models. Unequal device participation, differing data and communication constraints complicate evaluation. It is a design space with workload-specific tradeoffs, rather than a drop-in replacement for every centralized training system.
Communication-Efficient Learning of Deep Networks from Decentralized Data — McMahan and colleagues / arXiv · Source date: 2016-02-17 · Checked