Active Learning for Accurate Estimation of Linear Models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Active Learning for Accurate Estimation of Linear Models

Carlos Riquelme
Alessandro Lazaric


We explore the sequential decision-making problem where the goal is to estimate a number of linear models uniformly well, given a shared budget of random contexts independently sampled from a known distribution. For each incoming context, the decision-maker selects one of the linear models and receives an observation that is corrupted by the unknown noise level of that model. We present Trace-UCB, an adaptive allocation algorithm that learns the models' noise levels while balancing contexts accordingly across them, and prove bounds for its simple regret in both expectation and high-probability. We extend the algorithm and its bounds to the high dimensional setting , where the number of linear models times the dimension of the contexts is more than the total budget of samples. Simulations with real data suggest that Trace-UCB is remarkably robust , outperforming a number of baselines even when its assumptions are violated.
Fichier principal
Vignette du fichier
active_learning_accurate_estimation_linear_models_supplementary.pdf (3.75 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01538762 , version 1 (14-06-2017)


  • HAL Id : hal-01538762 , version 1


Carlos Riquelme, Mohammad Ghavamzadeh, Alessandro Lazaric. Active Learning for Accurate Estimation of Linear Models. ICML 2017 - 34th International Conference on Machine Learning, Aug 2017, Sydney, Australia. pp.36. ⟨hal-01538762⟩
238 View
44 Download


Gmail Facebook X LinkedIn More