%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 14 0 R ] /Type /Pages /Count 11 >> 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 (We present an efficient and practical algorithm for the online prediction of discrete\055time linear dynamical systems with a symmetric transition matrix\056 We circumvent the non\055convex optimization problem using improper learning\072 carefully overparameterize the class of LDSs by a polylogarithmic factor\054 in exchange for convexity of the loss functions\056 From this arises a polynomial\055time algorithm with a near\055optimal regret guarantee\054 with an analogous sample complexity bound for agnostic learning\056 Our algorithm is based on a novel filtering technique\054 which may be of independent interest\072 we convolve the time series with the eigenvectors of a certain Hankel matrix\056) /Producer (PyPDF2) /Title (Learning Linear Dynamical Systems via Spectral Filtering) /Date (2017) /ModDate (D\07220180212205713\05508\04700\047) /Published (2017) /Type (Conference Proceedings) /firstpage (6702) /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 (Elad Hazan\054 Karan Singh\054 Cyril Zhang) /lastpage (6712) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 15 0 R /Parent 1 0 R /Type /Page /Resources 16 0 R /MediaBox [ 0 0 612 792 ] >> endobj 5 0 obj << /Contents 38 0 R /Parent 1 0 R /Resources 39 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 68 0 R 69 0 R 70 0 R 71 0 R 72 0 R 73 0 R 74 0 R 75 0 R 76 0 R ] /Type /Page >> endobj 6 0 obj << /Contents 77 0 R /Parent 1 0 R /Resources 78 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 95 0 R 96 0 R 97 0 R 98 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 99 0 R /Parent 1 0 R /Resources 100 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 101 0 R 102 0 R 103 0 R 104 0 R 105 0 R 106 0 R 107 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 108 0 R /Parent 1 0 R /Resources 109 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 122 0 R 123 0 R 124 0 R 125 0 R 126 0 R 127 0 R 128 0 R 129 0 R 130 0 R 131 0 R 132 0 R 133 0 R 134 0 R 135 0 R 136 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 137 0 R /Parent 1 0 R /Resources 138 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 201 0 R 202 0 R 203 0 R 204 0 R 205 0 R 206 0 R 207 0 R 208 0 R 209 0 R 210 0 R 211 0 R 212 0 R 213 0 R 214 0 R 215 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 216 0 R /Parent 1 0 R /Resources 217 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 218 0 R 219 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 220 0 R /Parent 1 0 R /Resources 221 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 226 0 R 227 0 R 228 0 R 229 0 R 230 0 R 231 0 R 232 0 R 233 0 R 234 0 R 235 0 R 236 0 R 237 0 R 238 0 R 239 0 R 240 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 241 0 R /Parent 1 0 R /Resources 242 0 R /Group 279 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 281 0 R 282 0 R ] /Type /Page >> endobj 13 0 obj << /Contents 283 0 R /Parent 1 0 R /Type /Page /Resources 284 0 R /MediaBox [ 0 0 612 792 ] >> endobj 14 0 obj << /Contents 285 0 R /Parent 1 0 R /Type /Page /Resources 286 0 R /MediaBox [ 0 0 612 792 ] >> endobj 15 0 obj << /Length 2731 /Filter /FlateDecode >> stream xڅY˖WpW-)(5NΉ6I C#s N6Wu[U`uZ>w?B|U | r?U<0e3?}|8Z[? dxD30Yeߥ{kn^[&JmՒۯmTeQKõLӯ}af~$MwQ*} x1йeoz0ﮒ;?t_~ V ^Wf7ùYŢ(n;u],UY]JϹEqH2;$Lx,3^K iYkm.#iKVR?KvwyӔfmR#jf~oe m2ML ,(R监ƁMsKwF5