%PDF-1.3 1 0 obj << /Kids [ 4 0 R 5 0 R 6 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R 13 0 R ] /Type /Pages /Count 10 >> endobj 2 0 obj << /Subject (Neural Information Processing Systems http\072\057\057nips\056cc\057) /Publisher (Curran Associates\054 Inc\056) /Language (en\055US) /Created (2019) /EventType (Poster) /Description-Abstract (In this paper\054 we provide a method to learn the directed structure of a Bayesian network using data\056 The data is accessed by making conditional probability queries to a black\055box model\056 We introduce a notion of simplicity of representation of conditional probability tables for the nodes in the Bayesian network\054 that we call \140\140low rankness\047\047\056 We connect this notion to the Fourier transformation of real valued set functions and propose a method which learns the exact directed structure of a \140low rank\140 Bayesian network using very few queries\056 We formally prove that our method correctly recovers the true directed structure\054 runs in polynomial time and only needs polynomial samples with respect to the number of nodes\056 We also provide further improvements in efficiency if we have access to some observational data\056) /Producer (PyPDF2) /Title (Learning Bayesian Networks with Low Rank Conditional Probability Tables) /Date (2019) /ModDate (D\07220200213022807\05508\04700\047) /Published (2019) /Type (Conference Proceedings) /firstpage (8964) /Book (Advances in Neural Information Processing Systems 32) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (H\056 Wallach and H\056 Larochelle and A\056 Beygelzimer and F\056 d\047Alch\351\055Buc and E\056 Fox and R\056 Garnett) /Author (Adarsh Barik\054 Jean Honorio) /lastpage (8973) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 14 0 R /Parent 1 0 R /Type /Page /Resources 15 0 R /MediaBox [ 0 0 612 792 ] >> endobj 5 0 obj << /Contents 34 0 R /Parent 1 0 R /Type /Page /Resources 35 0 R /MediaBox [ 0 0 612 792 ] >> endobj 6 0 obj << /Contents 88 0 R /Parent 1 0 R /Type /Page /Resources 89 0 R /MediaBox [ 0 0 612 792 ] >> endobj 7 0 obj << /Contents 110 0 R /Parent 1 0 R /Type /Page /Resources 111 0 R /MediaBox [ 0 0 612 792 ] >> endobj 8 0 obj << /Contents 116 0 R /Parent 1 0 R /Type /Page /Resources 117 0 R /MediaBox [ 0 0 612 792 ] >> endobj 9 0 obj << /Contents 126 0 R /Parent 1 0 R /Type /Page /Resources 127 0 R /MediaBox [ 0 0 612 792 ] >> endobj 10 0 obj << /Contents 136 0 R /Parent 1 0 R /Type /Page /Resources 137 0 R /MediaBox [ 0 0 612 792 ] >> endobj 11 0 obj << /Contents 154 0 R /Parent 1 0 R /Type /Page /Resources 155 0 R /MediaBox [ 0 0 612 792 ] >> endobj 12 0 obj << /Contents 156 0 R /Parent 1 0 R /Type /Page /Resources 157 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Contents 158 0 R /Parent 1 0 R /Type /Page /Resources 159 0 R /MediaBox [ 0 0 612 792 ] >> endobj 14 0 obj << /Length 3199 /Filter /FlateDecode >> stream xڵZY~_GJcp[)˱9r^4_{p+*