Statistical Learning
Near-Optimal Comparison Based Clustering
The goal of clustering is to group similar objects into meaningful partitions.
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems
We then use these approximate subclass labels as a form of noisy supervision in a distributionally robust optimization objective.
The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers
We revisit the problem of supervised classification using quadratic features of the data. We do so to highlight the influence of properties of data distrbution on the generalization error.
Gaussian Copula Embeddings
Representation learning is a prominent machine learning approach for working with originally non-vectorial data.
Coordinate Linear Variance Reduction for Generalized Linear Programming
For better scalability, stochastic counterparts of these methods have been proposed.
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Sampling is a fundamental and arguably very important task with numerous applications in Machine Learning.