3 papers
cs.LG2012
Optimal Computational Trade-Off of Inexact Proximal Methods
Pierre Machart, Sandrine Anthoine, Luca Baldassarre
In this paper, we investigate the trade-off between convergence rate and computational cost when minimizing a composite functional with proximal-gradient methods, which are popular…
cs.LG2012
Confusion Matrix Stability Bounds for Multiclass Classification
Pierre Machart, Liva Ralaivola
In this paper, we provide new theoretical results on the generalization properties of learning algorithms for multiclass classification problems. The originality of our work is tha…
cs.LG2012
Stochastic Low-Rank Kernel Learning for Regression
Pierre Machart, Thomas Peel, Liva Ralaivola +2
We present a novel approach to learn a kernel-based regression function. It is based on the useof conical combinations of data-based parameterized kernels and on a new stochastic c…