uniform convergence
Country:
- Asia > Middle East > Jordan (0.04)
- North America > United States > Washington > King County > Seattle (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
Information Theoretic Lower Bounds for Information Theoretic Upper Bounds Roi Livni Department Electrical Engineering Tel Aviv University rlivni@tauex.tau.ac.il
But nonetheless, they tend to perform well on unseen test data.
Country:
- Asia > Middle East > Israel > Tel Aviv District > Tel Aviv (0.40)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- Asia > Middle East > Israel > Tel Aviv District > Tel Aviv (0.04)
Graph-based Discriminators: Sample Complexity and Expressiveness
Abasic question inlearning theory istoidentify iftwodistributions areidentical when we have access only to examples sampled from the distributions.
Country:
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > Netherlands > North Holland > Amsterdam (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Computational Learning Theory (0.31)
Country:
Genre:
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (0.93)
Technology:
Uniform convergence may be unable to explain generalization in deep learning
Vaishnavh Nagarajan, J. Zico Kolter
Neural Information Processing Systems http://nips.cc/
Country:
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.04)
- North America > Canada (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology:
SharperGeneralizationBoundsforPairwise Learning
We also introduce anew on-average stability measure to develop optimistic bounds in a low noise setting.
Country:
- North America > United States (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > Germany (0.04)
- Asia > China (0.04)
ConvexOptimization
We consider linear prediction with a convex Lipschitz loss, or more generally, stochastic convex optimization problems of generalized linear form, i.e.
Country:
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.04)
- Europe > Sweden > Stockholm > Stockholm (0.04)
- Europe > Austria > Styria > Graz (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.69)
Country:
- Asia > Middle East > Israel > Tel Aviv District > Tel Aviv (0.05)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Gradient Descent (1.00)
Country:
- North America > United States (0.14)
- Asia > Middle East > Israel > Tel Aviv District > Tel Aviv (0.04)
- North America > Canada (0.04)
- (2 more...)