Statistical Learning
Measuring Sample Quality with Stein's Method
Neural Information Processing Systems http://nips.cc/
GAP Safe screening rules for sparse multi-task and multi-class models
Eugene Ndiaye, Olivier Fercoq, Alexandre Gramfort, Joseph Salmon
Neural Information Processing Systems http://nips.cc/
On some provably correct cases of variational inference for topic models
Pranjal Awasthi, Andrej Risteski
Neural Information Processing Systems http://nips.cc/
Online Robust Regression via SGD on the null 1 loss
Robust learning is a critical field that seeks to develop efficient algorithms that can recover an underlying model despite possibly malicious corruptions in the data. In recent decades, being able to deal with corrupted measurements has become of crucial importance.
Graph Normalizing Flows
Jenny Liu, Aviral Kumar, Jimmy Ba, Jamie Kiros, Kevin Swersky
Conversely, GRevNets get the exact gradients at a minor additional cost, equivalent to one extra forward pass.
Multi-Layer Feature Reduction for Tree Structured Group Lasso via Hierarchical Projection
Neural Information Processing Systems http://nips.cc/
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks
Guodong Zhang, James Martens, Roger B. Grosse
We further extend our analysis to more general loss functions.