Active Learning for Accurate Estimation ...
Document type :
Communication dans un congrès avec actes
Title :
Active Learning for Accurate Estimation of Linear Models
Author(s) :
Riquelme, Carlos [Auteur]
Stanford University
Ghavamzadeh, Mohammad [Auteur]
Sequential Learning [SEQUEL]
Adobe Systems Inc. [Adobe Advanced Technology Labs]
Lazaric, Alessandro [Auteur]
Sequential Learning [SEQUEL]
Stanford University
Ghavamzadeh, Mohammad [Auteur]
Sequential Learning [SEQUEL]
Adobe Systems Inc. [Adobe Advanced Technology Labs]
Lazaric, Alessandro [Auteur]
![refId](/themes/Mirage2//images/idref.png)
Sequential Learning [SEQUEL]
Conference title :
ICML 2017 - 34th International Conference on Machine Learning
City :
Sydney
Country :
Australie
Start date of the conference :
2017-08-06
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- https://hal.inria.fr/hal-01538762/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01538762/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01538762/document
- Open access
- Access the document
- document
- Open access
- Access the document
- active_learning_accurate_estimation_linear_models_supplementary.pdf
- Open access
- Access the document