Doorkeeper

Talk by Arun Verma (IIT, Mumbai, India): Online Algorithm for Cost-Sensitive Unsupervised Learning

Tue, 09 Apr 2019 16:00 - 17:00

RIKEN AIP (Nihombashi) Open area

Register

Registration is closed

Get invited to future events

Free admission

Description

Title: Online Algorithm for Cost-Sensitive Unsupervised Learning

Abstract: In many security and healthcare systems, the detection and diagnosis systems use a sequence of sensors/tests. Each test outputs a prediction of the latent state and carries an inherent cost. However, the correctness of the predictions cannot be evaluated due to unavailability of the ground-truth annotations. Our objective is to learn strategies for selecting a test that gives the best trade-off between accuracy and costs in such Unsupervised Sensor Selection (USS) problems. Clearly, learning is feasible only if ground truth can be inferred (explicitly or implicitly) from the problem structure. It is observed that this happens if the problem satisfies the `Weak Dominance' (WD) property. We set up the USS problem as a stochastic partial monitoring problem and develop an algorithm with sub-linear regret under the WD property. We argue that our algorithm is optimal and evaluate its performance on problem instances generated from synthetic and real-world datasets.

About this community

RIKEN AIP Public

RIKEN AIP Public

Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community