compression scheme
Country:
- North America > United States > District of Columbia > Washington (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Europe > Germany (0.04)
- (3 more...)
Technology:
Country:
- North America > United States > Michigan > Washtenaw County > Ann Arbor (0.14)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Computational Learning Theory (0.46)
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Asia > Afghanistan > Parwan Province > Charikar (0.04)
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization
Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi
Neural Information Processing Systems http://nips.cc/
Country:
- Europe > Switzerland > Vaud > Lausanne (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > Switzerland > Zürich > Zürich (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.97)
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
Formixtures of axis-aligned Gaussians, we show thateO(kd/ε2)samples suffice, matching a knownlowerbound.
Country:
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.05)
- North America > Canada > Quebec > Montreal (0.05)
- North America > United States > New York > New York County > New York City (0.04)
- (3 more...)
Country:
- North America > United States > New Mexico > Los Alamos County > Los Alamos (0.04)
- Oceania > Australia > New South Wales > Sydney (0.04)
- Asia > China > Shanghai > Shanghai (0.04)
- Asia > China > Jiangsu Province > Nanjing (0.04)
Technology:
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.46)
Country:
- North America > Canada > Ontario > Toronto (0.14)
- Europe > Spain > Andalusia > Cádiz Province > Cadiz (0.04)
Technology:
TowardsaUnified Information-Theoretic FrameworkforGeneralization
Let D be an unknown distribution on a spaceZ, and let H be a set of classifiers. Consider a (randomized) learning algorithmA = (An)n 1 that selects an elementˆh in H, based onn i.i.d.
Country:
- North America > Canada > Ontario (0.04)
- Europe > Spain > Andalusia > Cádiz Province > Cadiz (0.04)
Industry:
- Health & Medicine (0.67)
- Education (0.46)
Technology: