Statistical Learning
Acceleration and Averaging in Stochastic Descent Dynamics
Walid Krichene, Peter L. Bartlett
Neural Information Processing Systems http://nips.cc/
On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks
Arturs Backurs, Piotr Indyk, Ludwig Schmidt
Empirical risk minimization (ERM) is ubiquitous in machine learning and underlies most supervised learning methods.
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Francesco Locatello, Michael Tschannen, Gunnar Raetsch, Martin Jaggi
Neural Information Processing Systems http://nips.cc/
Gaussian Quadrature for Kernel Features
Kernel methods have recently attracted resurgent interest, showing performance competitive with deep neural networks in tasks such as speech recognition.
Practical Hash Functions for Similarity Estimation and Dimensionality Reduction
Søren Dahlgaard, Mathias Knudsen, Mikkel Thorup
Neural Information Processing Systems http://nips.cc/
Federated Multi-Task Learning
Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi, Ameet S. Talwalkar
Following [25, 36, 26], we summarize the unique challenges of federated learning below.
Predictive-State Decoders: Encoding the Future into Recurrent Networks
Arun Venkatraman, Nicholas Rhinehart, Wen Sun, Lerrel Pinto, Martial Hebert, Byron Boots, Kris Kitani, J. Bagnell
Despite their wide success in a variety of domains, recurrent neural networks (RNNs) are often inhibited by the difficulty of learning an internal state representation.
A scaled Bregman theorem with applications
Richard Nock, Aditya Menon, Cheng Soon Ong
Bregman divergence properties that have been pervasive in machine learning.
Generalization Properties of Learning with Random Features
Alessandro Rudi, Lorenzo Rosasco
We study the generalization properties of ridge regression with random features in the statistical learning framework.
Improved Graph Laplacian via Geometric Self-Consistency
Dominique Joncas, Marina Meila, James McQueen
We address this problem by choosing a quality criterion for the Laplacian, that measures its ability to preserve the geometry of the data.