An Optimal Policy for Target Localization with Application to Electron Microscopy

This paper considers the task of finding a target location by making a limited number of sequential observations. Each observation results from evaluating an imperfect classifier of a chosen cost and accuracy on an interval of chosen length and position. Within a Bayesian framework, we study the problem of minimizing an objective that combines the entropy of the posterior distribution with the cost of the questions asked. In this problem, we show that the one-step lookahead policy is Bayes-optimal for any arbitrary time horizon. Moreover, this one-step lookahead policy is easy to compute and implement. We then use this policy in the context of localizing mitochondria in electron microscope images, and experimentally show that significant speed ups in acquisition can be gained, while maintaining near equal image quality at target locations, when compared to current policies.

[1]  Peter I. Frazier,et al.  A Bayesian approach to stochastic root finding , 2011, Proceedings of the 2011 Winter Simulation Conference (WSC).

[2]  Michael Horstein,et al.  Sequential transmission using noiseless feedback , 1963, IEEE Trans. Inf. Theory.

[3]  R. Nowak,et al.  Generalized binary search , 2008, 2008 46th Annual Allerton Conference on Communication, Control, and Computing.

[4]  Onésimo Hernández-Lerma,et al.  Controlled Markov Processes , 1965 .

[5]  R. Nowak,et al.  Active Sensing and Learning , 2011 .

[6]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[7]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[8]  Sanjoy Dasgupta,et al.  A General Agnostic Active Learning Algorithm , 2007, ISAIM.

[9]  Raphael Sznitman,et al.  Active Testing for Face Detection and Localization , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Sanmay Das,et al.  Near-Optimal Target Learning With Stochastic Binary Signals , 2011, UAI.

[11]  M. Degroot.  Optimal Statistical Decisions , 1970 .

[12]  Pascal Fua,et al.  Efficient Scanning for EM Based Target Localization , 2012, MICCAI.

[13]  Robert D. Nowak,et al.  Faster Rates in Regression via Active Learning , 2005, NIPS.

[14]  Peter Winkler,et al.  On playing “Twenty Questions” with a liar , 1992, SODA '92.

[15]  Twenty Questions with Noise: Bayes Optimal Policies for Entropy Loss , 2012, Journal of Applied Probability.

[16]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[17]  Yi Zhang,et al.  Exploration and Exploitation in Adaptive Filtering Based on Bayesian Active Learning , 2003, ICML.

[18]  Ashok Veeraraghavan,et al.  Increasing depth resolution of electron microscopy of neural circuits using sparse tomographic reconstruction , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Peter I. Frazier,et al.  Sequential Sampling with Economics of Selection Procedures , 2012, Manag. Sci..

[20]  Robert D. Nowak,et al.  Distilled Sensing: Adaptive Sampling for Sparse Detection and Estimation , 2010, IEEE Transactions on Information Theory.

[21]  G. Barrie Wetherill,et al.  Sequential methods in statistics , 1967 .

[22]  Peter Winkler,et al.  Three Thresholds for a Liar , 1992, Combinatorics, Probability and Computing.

[23]  Avinatan Hassidim,et al.  The Bayesian Learner is Optimal for Noisy Binary Search  (and Pretty Good for Quantum as Well) , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[24]  Pascal Fua,et al.  Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features , 2012, IEEE Transactions on Medical Imaging.

[25]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

[26]  P. W. Jones,et al.  Bandit Problems, Sequential Allocation of Experiments , 1987 .

[27]  Nando de Freitas,et al.  A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning , 2010, ArXiv.