Timezone: »

Active Learning for Accurate Estimation of Linear Models
Carlos Riquelme Ruiz · Mohammad Ghavamzadeh · Alessandro Lazaric

Tue Aug 08 01:30 AM -- 05:00 AM (PDT) @ Gallery #14

We explore the sequential decision making problem where the goal is to estimate uniformly well a number of linear models, given a shared budget of random contexts independently sampled from a known distribution. The decision maker must query one of the linear models for each incoming context, and receives an observation corrupted by noise levels that are unknown, and depend on the model instance. We present Trace-UCB, an adaptive allocation algorithm that learns the noise levels while balancing contexts accordingly across the different linear functions, and derive guarantees for simple regret in both expectation and high-probability. Finally, we extend the algorithm and its guarantees to high dimensional settings, where the number of linear models times the dimension of the contextual space is higher 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.

Author Information

Carlos Riquelme Ruiz (Stanford University)
Mohammad Ghavamzadeh (Adobe Research & INRIA)
Alessandro Lazaric (FACEBOOK)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors