%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 (2017) /EventType (Poster) /Description-Abstract (Stein variational gradient descent \050SVGD\051 is a deterministic sampling algorithm that iteratively transports a set of particles to approximate given distributions\054 based on a gradient\055based update constructed to optimally decrease the KL divergence within a function space\056 This paper develops the first theoretical analysis on SVGD\056 We establish that the empirical measures of the SVGD samples weakly converge to the target distribution\054 and show that the asymptotic behavior of SVGD is characterized by a nonlinear Fokker\055Planck equation known as Vlasov equation in physics\056 We develop a geometric perspective that views SVGD as a gradient flow of the KL divergence functional under a new metric structure on the space of distributions induced by Stein operator\056) /Producer (PyPDF2) /Title (Stein Variational Gradient Descent as Gradient Flow) /Date (2017) /ModDate (D\07220180212234450\05508\04700\047) /Published (2017) /Type (Conference Proceedings) /firstpage (3115) /Book (Advances in Neural Information Processing Systems 30) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (I\056 Guyon and U\056V\056 Luxburg and S\056 Bengio and H\056 Wallach and R\056 Fergus and S\056 Vishwanathan and R\056 Garnett) /Author (Qiang Liu) /lastpage (3123) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 13 0 R /Parent 1 0 R /Resources 14 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 44 0 R 45 0 R 46 0 R 47 0 R ] /Type /Page >> endobj 5 0 obj << /Contents 48 0 R /Parent 1 0 R /Resources 49 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 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 << /Contents 104 0 R /Parent 1 0 R /Resources 105 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 106 0 R 107 0 R 108 0 R 109 0 R 110 0 R 111 0 R 112 0 R 113 0 R 114 0 R 115 0 R 116 0 R 117 0 R 118 0 R 119 0 R 120 0 R 121 0 R 122 0 R 123 0 R 124 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 125 0 R /Parent 1 0 R /Resources 126 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 131 0 R 132 0 R 133 0 R 134 0 R 135 0 R 136 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 137 0 R /Parent 1 0 R /Resources 138 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 139 0 R 140 0 R 141 0 R 142 0 R 143 0 R 144 0 R 145 0 R 146 0 R 147 0 R 148 0 R 149 0 R 150 0 R 151 0 R 152 0 R 153 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 154 0 R /Parent 1 0 R /Resources 155 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 162 0 R 163 0 R 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 175 0 R 176 0 R 177 0 R 178 0 R 179 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 180 0 R /Parent 1 0 R /Resources 181 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 182 0 R 183 0 R 184 0 R 185 0 R 186 0 R 187 0 R 188 0 R 189 0 R 190 0 R 191 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 192 0 R /Parent 1 0 R /Resources 193 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 194 0 R 195 0 R 196 0 R 197 0 R 198 0 R 199 0 R 200 0 R 201 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 202 0 R /Parent 1 0 R /Type /Page /Resources 203 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 3269 /Filter /FlateDecode >> stream xڕZKs6WHU\U;yO6IMNŕh58ίHTE$@RZ}{Ξ$xUJT*TIoTUft7&3uUX*/ʸBv>_LE+c[W~;۶g.}LPO| DE/|p&vL+ڢ+b*jխ=-uNJ2DP2a%~n=y<6&Y%XKU
bQi2u:Io{µ]k7gov
WMе_<F,6fq]M2j1/$]\N{M?q\cjd5<ɜMHy8gofl:YIzj#8qY=w