%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 ] /Type /Pages /Count 9 >> 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 (2015) /EventType (Poster) /Description-Abstract (We consider a sequential learning problem with Gaussian payoffs and side information\072 after selecting an action \044i\044\054 the learner receives information about the payoff of every action \044j\044 in the form of Gaussian observations whose mean is the same as the mean payoff\054 but the variance depends on the pair \044\050i\054j\051\044 \050and may be infinite\051\056 The setup allows a more refined information transfer from one action to another than previous partial monitoring setups\054 including the recently introduced graph\055structured feedback case\056 For the first time in the literature\054 we provide non\055asymptotic problem\055dependent lower bounds on the regret of any algorithm\054 which recover existing asymptotic problem\055dependent lower bounds and finite\055time minimax lower bounds available in the literature\056 We also provide algorithms that achieve the problem\055dependent lower bound \050up to some universal constant factor\051 or the minimax lower bounds \050up to logarithmic factors\051\056) /Producer (PyPDF2) /Title (Online Learning with Gaussian Payoffs and Side Observations) /Date (2015) /ModDate (D\07220151218153407\05508\04700\047) /Published (2015) /Type (Conference Proceedings) /firstpage (1360) /Book (Advances in Neural Information Processing Systems 28) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (C\056 Cortes and N\056D\056 Lawrence and D\056D\056 Lee and M\056 Sugiyama and R\056 Garnett and R\056 Garnett) /Author (Yifan Wu\054 Andr\341s Gy\366rgy\054 Csaba Szepesvari) /lastpage (1368) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Parent 1 0 R /Contents 13 0 R /Resources 14 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 47 0 R 48 0 R 49 0 R 50 0 R 51 0 R 52 0 R 53 0 R 54 0 R 55 0 R 56 0 R 57 0 R 58 0 R 59 0 R 60 0 R 61 0 R ] /Type /Page >> endobj 5 0 obj << /Parent 1 0 R /Contents 62 0 R /Resources 63 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 88 0 R 89 0 R 90 0 R 91 0 R 92 0 R 93 0 R 94 0 R 95 0 R 96 0 R 97 0 R 98 0 R 99 0 R 100 0 R 101 0 R 102 0 R 103 0 R ] /Type /Page >> endobj 6 0 obj << /Parent 1 0 R /Contents 104 0 R /Resources 105 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 114 0 R 115 0 R 116 0 R 117 0 R 118 0 R ] /Type /Page >> endobj 7 0 obj << /Parent 1 0 R /Contents 119 0 R /Resources 120 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 129 0 R 130 0 R 131 0 R 132 0 R 133 0 R ] /Type /Page >> endobj 8 0 obj << /Parent 1 0 R /Contents 134 0 R /Resources 135 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 156 0 R 157 0 R 158 0 R 159 0 R 160 0 R 161 0 R ] /Type /Page >> endobj 9 0 obj << /Parent 1 0 R /Contents 162 0 R /Resources 163 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 164 0 R 165 0 R 166 0 R 167 0 R 168 0 R 169 0 R 170 0 R 171 0 R 172 0 R 173 0 R 174 0 R ] /Type /Page >> endobj 10 0 obj << /Parent 1 0 R /Contents 175 0 R /Resources 176 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 177 0 R 178 0 R 179 0 R 180 0 R 181 0 R 182 0 R 183 0 R 184 0 R 185 0 R 186 0 R 187 0 R 188 0 R ] /Type /Page >> endobj 11 0 obj << /Parent 1 0 R /Contents 189 0 R /Resources 190 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 191 0 R 192 0 R ] /Type /Page >> endobj 12 0 obj << /Parent 1 0 R /Contents 193 0 R /Type /Page /Resources 194 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 3162 /Filter /FlateDecode >> stream xڍZ[s~У4c1D4Md:qLDQz(B!);ʯL7}1]~pCx!oVQX.%DU"[?==|}yGYz:84_)PGyMYkeMf~07Q6M14{n|j쨃"Umg㮫ZJ5r?|tciZ/j?@ov&U4QR"