17 citations · 28 across the 7 of their papers we have counts for
7 papers
Online Parameter-Free Learning of Multiple Low Variance Tasks
Giulia Denevi, Dimitris Stamos, Massimiliano Pontil
We propose a method to learn a common bias vector for a growing sequence of low-variance tasks. Unlike state-of-the-art approaches, our method does not require tuning any hyper-par…
Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction
Giulia Luise, Dimitris Stamos, Massimiliano Pontil +1
We study the interplay between surrogate methods for structured prediction and techniques from multitask learning designed to leverage relationships between surrogate outputs. We p…
Incremental Learning-to-Learn with Statistical Guarantees
Giulia Denevi, Carlo Ciliberto, Dimitris Stamos +1
In learning-to-learn the goal is to infer a learning algorithm that works well on a class of tasks sampled from an unknown meta distribution. In contrast to previous work on batch…
Reexamining Low Rank Matrix Factorization for Trace Norm Regularization
Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil
Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix f…
Fitting Spectral Decay with the -Support Norm
Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos
The spectral -support norm enjoys good estimation properties in low rank matrix learning problems, empirically outperforming the trace norm. Its unit ball is the convex hull of…
New Perspectives on -Support and Cluster Norms
Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos
We study a regularizer which is defined as a parameterized infimum of quadratics, and which we call the box-norm. We show that the k-support norm, a regularizer proposed by [Argyri…