Robust Probabilistic Inference

Robust probabilistic inference is an extension of probabilistic inference, where some of the observations are adversarially corrupted. We model it as a zero-sum game between the adversary, who can select a modification rule, and the predictor, who wants to accurately predict the state of nature. Given a black-box access to a Bayesian inference in the classic (adversary-free) setting, our near optimal policy runs in polynomial time in the number of observations and the number of possible modification rules.

[1]  Dana Ron,et al.  Best of Two Local Models: Local Centralized and Local Distributed Algorithms , 2014, ArXiv.

[2]  Ronitt Rubinfeld,et al.  Fast Local Computation Algorithms , 2011, ICS.

[3]  James K. Ho,et al.  Decomposition of linear programs using parallel computation , 1988, Math. Program..

[4]  Mihalis Yannakakis,et al.  Linear programming without the matrix , 1993, STOC.

[5]  Nathan Linial,et al.  Collective coin flipping, robust voting schemes and minima of Banzhaf values , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[6]  Avinatan Hassidim,et al.  Local computation mechanism design , 2013, EC.

[7]  Nathan Linial,et al.  The influence of variables on Boolean functions , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[8]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[9]  Ronitt Rubinfeld,et al.  Local Algorithms for Sparse Spanning Graphs , 2014, APPROX-RANDOM.

[10]  Leonid Khachiyan,et al.  Approximate minimum-cost multicommodity flows in $$\tilde O$$ (ɛ−2KNM) timetime , 1996, Math. Program..

[11]  Éva Tardos,et al.  Fast Approximation Algorithms for Fractional Packing and Covering Problems , 1995, Math. Oper. Res..

[12]  George B. Dantzig,et al.  Decomposition Principle for Linear Programs , 1960 .

[13]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[14]  Ryan O'Donnell,et al.  Noise stability of functions with low influences: Invariance and optimality , 2005, 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05).

[15]  Omer Reingold,et al.  New techniques and tighter bounds for local computation algorithms , 2014, J. Comput. Syst. Sci..

[16]  Noam Nisan,et al.  A parallel approximation algorithm for positive linear programming , 1993, STOC.

[17]  Yishay Mansour,et al.  Converting Online Algorithms to Local Computation Algorithms , 2012, ICALP.

[18]  Rahul Jain,et al.  A Parallel Approximation Algorithm for Positive Semidefinite Programming , 2011, 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science.

[19]  Yishay Mansour,et al.  A Local Computation Approximation Scheme to Maximum Matching , 2013, APPROX-RANDOM.

[20]  Noga Alon,et al.  Space-efficient local computation algorithms , 2011, SODA.