Achievable distributional robustness when the robust risk is only partially identified
–Neural Information Processing Systems
In safety-critical applications, machine learning models should generalize well under worst-case distribution shifts, that is, have a small robust risk.
Neural Information Processing Systems
Feb-16-2026, 20:54:13 GMT
- Country:
- Europe
- Switzerland > Zürich
- Zürich (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Switzerland > Zürich
- North America > United States (0.04)
- Europe
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Health & Medicine (0.46)
- Information Technology (0.45)
- Technology: