Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes
Hassan Ashtiani, Shai Ben-David, Nicholas Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan
–Neural Information Processing Systems
Formixtures of axis-aligned Gaussians, we show thateO(kd/ε2)samples suffice, matching a knownlowerbound.
Neural Information Processing Systems
Feb-13-2026, 04:03:09 GMT
- Country:
- North America
- United States
- New York > New York County
- New York City (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- New York > New York County
- Canada
- Quebec > Montreal (0.05)
- Ontario > Waterloo Region
- Waterloo (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.05)
- United States
- Europe > Netherlands
- South Holland > Leiden (0.04)
- North America
- Technology: