Statistical Learning
Learning To Learn Around A Common Mean
Giulia Denevi, Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil
Neural Information Processing Systems http://nips.cc/
Learning without the Phase: Regularized PhaseMax Achieves Optimal Sample Complexity
Fariborz Salehi, Ehsan Abbasi, Babak Hassibi
's are the rows of a known measurement matrix
Constrained Graph Variational Autoencoders for Molecule Design
Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander Gaunt
Neural Information Processing Systems http://nips.cc/
Infinite-Horizon Gaussian Processes
Arno Solin, James Hensman, Richard E. Turner
This work was undertaken whilst AS was a Visiting Research Fellow with University of Cambridge.
The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning
Semi-supervised learning has been reported to deliver encouraging results in various settings, e.g. for object detection in computer vision (Rasmus et al., 2015), protein function prediction from sequence data (Weston et al., 2005) or prediction of cancer recurrence (Shi & Zhang, 2011) in the
Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification
Dimitrios Milios, Raffaello Camoriano, Pietro Michiardi, Lorenzo Rosasco, Maurizio Filippone
Neural Information Processing Systems http://nips.cc/
Generalizing Point Embeddings using the Wasserstein Space of Elliptical Distributions
Such embeddings have been traditionally recovered by seeking isometric embeddings in lower dimensional Euclidean spaces, as studied in [Johnson and Lindenstrauss, 1984, Bourgain, 1985].
Large Scale computation of Means and Clusters for Persistence Diagrams using Optimal Transport
Theo Lacombe, Marco Cuturi, Steve OUDOT
Topological data analysis (TDA) has been used successfully in a wide array of applications, for instance in medical (Nicolau et al., 2011) or material (Hiraoka et al., 2016) sciences, computer vision (Li et al., 2014) or to classify NBA players (Lum et al., 2013).
Model Agnostic Supervised Local Explanations
Gregory Plumb, Denali Molitor, Ameet S. Talwalkar
Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations.
Convergence of Cubic Regularization for Nonconvex Optimization under KL Property
Yi Zhou, Zhe Wang, Yingbin Liang
Cubic-regularized Newton's method (CR) is a popular algorithm that guarantees