1<!DOCTYPE html> 2<html lang="en"> 3 4 <head> 5 6 <meta charset="utf-8"> 7<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> 8<meta http-equiv="X-UA-Compatible" content="IE=edge"> 9 10<title> 11 12 Saurabh Sihag 13 14 15</title> 16<meta name="description" content="A simple, whitespace theme for academics. Based on [*folio](https://github.com/bogoli/-folio) design. 17"> 18 19<!-- Open Graph --> 20 21 22<!-- Bootstrap & MDB --> 23<link href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css" rel="stylesheet" integrity="sha512-MoRNloxbStBcD8z3M/2BmnT+rg4IsMxPkXaGh2zD6LGNNFE80W3onsAhRcMAMrSoyWL9xD7Ert0men7vR8LUZg==" crossorigin="anonymous"> 24<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/mdbootstrap/4.19.1/css/mdb.min.css" integrity="sha512-RO38pBRxYH3SoOprtPTD86JFOclM51/XTIdEPh5j8sj4tp8jmQIx26twG52UaLi//hQldfrh7e51WzP9wuP32Q==" crossorigin="anonymous" /> 25 26<!-- Fonts & Icons --> 27<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.14.0/css/all.min.css" integrity="sha512-1PKOgIY59xJ8Co8+NE6FZ+LOAZKjy+KY8iq0G4B3CyeY6wYHN3yt9PW0XpSriVlkMXe40PTKnXrLnZ9+fkDaog==" crossorigin="anonymous"> 28<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/academicons/1.9.0/css/academicons.min.css" integrity="sha512-W4yqoT1+8NLkinBLBZko+dFB2ZbHsYLDdr50VElllRcNt2Q4/GSs6u71UHKxB7S6JEMCp5Ve4xjh3eGQl/HRvg==" crossorigin="anonymous"> 29<link rel="stylesheet" type="text/css" href="https://fonts.googleapis.com/css?family=Roboto:300,400,500,700|Roboto+Slab:100,300,400,500,700|Material+Icons"> 30 31<!-- Code Syntax Highlighting --> 32<link rel="stylesheet" href="https://gitcdn.link/repo/jwarby/jekyll-pygments-themes/master/github.css" /> 33 34<!-- Styles --> 35 36<link rel="icon" href="data:image/svg+xml,<svg xmlns=%22http://www.w3.org/2000/svg%22 viewBox=%220 0 100 100%22><text y=%22.9em%22 font-size=%2290%22> </text></svg>"> 37 38<link rel="stylesheet" href="/assets/css/main.css"> 39<link rel="canonical" href="http://localhost:4000/"> 40 41 42<!-- Dark Mode -->
43<script src="/assets/js/theme.js"></script>
vendor: 1 bytes, line 43
43
44<script src="/assets/js/dark_mode.js"></script>
44 45 46 47 </head> 48 49 <body class=" "> 50 51 <!-- Header --> 52 53 <header> 54 55</header> 56 57 58 <!-- Content --> 59 60 <div class="container mt-5"> 61 <div class="post"> 62 63 <header class="post-header"> 64 <h1 class="post-title"> 65 <span class="font-weight-bold">Saurabh</span> Sihag 66 </h1> 67 <p class="desc">Assistant Professor at <a href="https://www.albany.edu/" target="_blank" rel="noopener noreferrer">University at Albany</a>.</p> 68 </header> 69 70 <article> 71 72 <div class="profile float-right"> 73 74 75 76 77<figure> 78 79 <picture> 80 81 <source media="(max-width: 480px)" srcset="/assets/img/pic_2024.jpg"> 82 83 <source media="(max-width: 800px)" srcset="/assets/img/pic_2024.jpg"> 84 85 <source media="(max-width: 1400px)" srcset="/assets/img/pic_2024.jpg"> 86 87 88 <!-- Fallback to the original file --> 89 <img class="img-fluid z-dept-1 rounded" src="/assets/img/pic_2024.jpg"> 90 91 </source></source></source></picture> 92 93 94 95</figure> 96 97 98 99 <div class="social"> 100 <div class="contact-icons"> 101 <a href="mailto:[email protected]" title="email"><i class="fas fa-envelope" style="font-size:32px"></i></a> 102 103<a href="https://scholar.google.com/citations?user=T8D94-QAAAAJ" title="Google Scholar" target="_blank" rel="noopener noreferrer"><i class="ai ai-google-scholar" style="font-size:32px"></i></a> 104 105<a href="https://dblp.org/pid/172/0928.html" title="DBLP" target="_blank" rel="noopener noreferrer"><i class="ai ai-dblp" style="font-size:32px"></i></a> 106 107<a href="https://www.linkedin.com/in/saurabh-sihag" title="LinkedIn" target="_blank" rel="noopener noreferrer"><i class="fab fa-linkedin" style="font-size:32px"></i></a> 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 </div> 123 <div class="contact-note"></div> 124 </div> 125 126 127 </div> 128 129 130 <div class="clearfix"> 131 <p>I am an Assistant Professor in the Electrical and Computer Engineering department at <a href="https://www.albany.edu/" target="_blank" rel="noopener noreferrer">State University of New York at Albany</a>. Previously, I was a postdoctoral researcher working with <a href="https://alelab.seas.upenn.edu/" target="_blank" rel="noopener noreferrer">Dr. Alejandro Ribeiro</a> at the University of Pennsylvania. Broadly, I study statistical inference and machine learning approaches over graph models, both from theoretic and algorithmic perspectives with applications in network neuroscience. I had received the PhD degree in Electrical Engineering at Rensselaer Polytechnic Institute in Dec., 2020, where I was advised by <a href="https://www.isg-rpi.com/" target="_blank" rel="noopener noreferrer">Dr. Ali Tajer</a>. My PhD thesis on Statistical Learning and Inference over Networks can be accessed <a href="https://www.proquest.com/docview/2501490179" target="_blank" rel="noopener noreferrer">here</a>.</p> 132 133<p>My research is focused on developing novel principles of machine learning and statistical inference using concepts from signal processing, learning theory, information theory, and graph theory. I have worked on a variety of research problems that include statistical learning of graph models (<a href="http://proceedings.mlr.press/v130/varici21a.html" target="_blank" rel="noopener noreferrer">AISTATS</a>, <a href="https://proceedings.neurips.cc/paper/2019/file/e025b6279c1b88d3ec0eca6fcb6e6280-Paper.pdf" target="_blank" rel="noopener noreferrer">NeurIPS</a>), state estimation in signal processing (<a href="https://ieeexplore.ieee.org/abstract/document/9057614" target="_blank" rel="noopener noreferrer">T-IT</a>, <a href="https://ieeexplore.ieee.org/abstract/document/8338162" target="_blank" rel="noopener noreferrer">JSTSP</a>, <a href="https://ieeexplore.ieee.org/abstract/document/8747440" target="_blank" rel="noopener noreferrer">SPL</a>), graph signal processing analyses of multimodal brain imaging data (<a href="https://ieeexplore.ieee.org/abstract/document/9044786" target="_blank" rel="noopener noreferrer">TSIPN</a>) and association of neuroimaging features with blood biomarkers (<a href="https://www.nature.com/articles/s43856-021-00065-5" target="_blank" rel="noopener noreferrer">NatCommsMed</a>), and adaptive graph-constrained group testing (<a href="https://ieeexplore.ieee.org/abstract/document/9658194" target="_blank" rel="noopener noreferrer">
133TSP</a>). Currently, I am investigating statistical inference using graph neural networks (<a href="https://proceedings.neurips.cc/paper_files/paper/2022/hash/6cb00ce1a21a090a3dae04cebebd8341-Abstract-Conference.html" target="_blank" rel="noopener noreferrer">VNN</a>), with brain age prediction as a recent application (<a href="https://arxiv.org/abs/2305.18370" target="_blank" rel="noopener noreferrer">VNN_Brain_Age</a>). A complete list of my research publications is available <a href="https://scholar.google.com/citations?user=T8D94-QAAAAJ" target="_blank" rel="noopener noreferrer">here</a>.</p> 134 135<!-- <p>The glimpses of my attempts at trail/road running and photography can be found <a href="https://www.strava.com/athletes/48840433" target="_blank" rel="noopener noreferrer">here</a> and <a href="https://www.instagram.com/solo_dyad/" target="_blank" rel="noopener noreferrer">here</a>.</p> --> 136 137 </div> 138 139 140 <div class="news"> 141 <h2>news</h2> 142 143 <div class="table-responsive"> 144 <table class="table table-sm table-borderless"> 145 <tr> 146 <th scope="row">April, 2026</th> 147 <td> 148 149 Paper on 'Brain Age Gap Progression in Individuals at Risk for Neurodegeneration' accepted at International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2026. 150 151 152 153 </td> 154 </tr> 155 156 157 <tr> 158 <th scope="row">April, 2026</th> 159 <td> 160 161 Served as a Reviewer for NIH Special Emphasis Panel on Biomarker Studies in Neuroscience. 162 163 164 </td> 165 </tr> 166 167 168 <tr> 169 <th scope="row">April, 2026</th> 170 <td> 171 172 Presented tutorial on 'Learning with Covariance Matrices: Foundations and Applications to Network Neuroscience' at IEEE International Symposium on Biomedical Imaging, 2026 (<a href="/assets/pdf/VNN_Tutorial_ISBI.pdf" target="blank">Slides</a>). 173 174 175 176 </td> 177 </tr> 178 179 180 181 <tr> 182 <th scope="row">August-September, 2025</th> 183 <td> 184 185 Presented tutorials on 'Learning with Covariance Matrices: Foundations and Applications to Network Neuroscience' at IEEE MLSP, 2025 (<a href="/assets/pdf/VNN_Tutorial_MLSP_final.pdf" target="blank">Slides</a>) and EUSIPCO, 2025 (<a href="/assets/pdf/VNN_Tutorial_EUSIPCO_compressed.pdf" target="blank">Slides</a>). 186 187 188 189 </td> 190 </tr> 191 192 <tr> 193 <th scope="row">September, 2025</th> 194 <td> 195 196 Presented a talk on 'Disentangling Neurodegeneration with Brain Age Gap Prediction Models' at TU Delft (<a href="/assets/pdf/VNN_Tutorial_Delft.pdf" target="blank">Slides</a>). 197 198 199 200 </td> 201 </tr> 202 203 204 205 206 <tr> 207 <th scope="row">July, 2025</th> 208 <td> 209 210 Paper on 'Disentangling Neurodegeneration with Brain Age Gap Prediction Models: A Graph Signal Processing Perspective' accepted at IEEE Signal Processing Magazine. Accepted paper available <a href="/assets/pdf/MSP3596731.pdf" target="blank">here</a>. 211 212 213 214 </td> 215 </tr> 216 217 <tr> 218 <th scope="row">January, 2025</th> 219 <td> 220 221 Paper on 'Explainable Brain Age Gap Prediction in Neurodegenerative Conditions Using coVariance Neural Networks' accepted at ISBI, 2025. 222 223 224 </td> 225 </tr> 226 227 <tr> 228 <th scope="row">May, 2024</th> 229 <td> 230 231 Paper on 'Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks' accepted at ICML, 2024. 232 233 234 </td> 235 </tr> 236 237 <tr> 238 <th scope="row">March, 2024</th> 239 <td> 240 241 Paper on 'Transferability of coVariance Neural Networks' accepted at IEEE Journal of Selected Topics in Signal Processing (JSTSP) Special Series on AI in Signal & Data Science. 242 243 244 </td> 245 </tr> 246 247 <tr> 248 <th scope="row">September, 2023</th> 249 <td> 250 251 Paper on 'Explainable Brain Age Prediction using coVariance Neural Networks' accepted at NeurIPS, 2023. 252 253 254 </td> 255 </tr> 256 257 <tr> 258 <th scope="row">June, 2023</th> 259 <td> 260 261 Paper on 'Learning Graph Structure from Convolutional Mixtures' accepted at Transactions on Machine Learning Research. 262 263 264 </td> 265 </tr> 266 267 268 <tr> 269 <th scope="row">June, 2023</th> 270 <td> 271 272 Paper on 'Predicting Brain Age using Transferable coVariance Neural Networks' was presented at ICASSP, 2023. 273 274 275 </td> 276 </tr> 277 278 <tr> 279 <th scope="row">Sep. 14, 2022</th> 280 <td> 281 282 Paper on 'coVariance Neural Networks' was accepted at NeurIPS, 2022. 283 284 285 </td> 286 </tr> 287 288 289 290 291 292 </table> 293 </div> 294 295</div> 296 297 298 299 300 </article> 301 302</div> 303 304 </div> 305 306 <!-- Footer --> 307 308 309<footer class="fixed-bottom"> 310 <div class="container mt-0"> 311 © Copyright 2021 Saurabh Sihag. 312 Powered by <a href="http://jekyllrb.com/" target="_blank" rel="noopener noreferrer">Jekyll</a> with <a href="https://github.com/alshedivat/al-folio" target="_blank" rel="noopener noreferrer">al-folio</a> theme. Hosted by <a href="https://pages.github.com/" target="_blank" rel="noopener noreferrer">GitHub Pages</a>. 313 314 315 316 </div> 317</footer> 318 319 320 321 </body> 322 323 <!-- jQuery -->
324<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.5.1/jquery.min.js" integrity="sha512-bLT0Qm9VnAYZDflyKcBaQ2gg0hSYNQrJ8RilYldYQ1FxQYoCLtUjuuRuZo+fjqhx/qtq/1itJ0C2ejDxltZVFg==" crossorigin="anonymous"></script>
324 325 326 <!-- Bootsrap & MDB scripts -->
327<script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/2.4.4/umd/popper.min.js" integrity="sha512-eUQ9hGdLjBjY3F41CScH3UX+4JDSI9zXeroz7hJ+RteoCaY+GP/LDoM8AO+Pt+DRFw3nXqsjh9Zsts8hnYv8/A==" crossorigin="anonymous"></script>
vendor: 1 bytes, line 327
327
328<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js" integrity="sha512-M5KW3ztuIICmVIhjSqXe01oV2bpe248gOxqmlcYrEzAvws7Pw3z6BK0iGbrwvdrUQUhi3eXgtxp5I8PDo9YfjQ==" crossorigin="anonymous"></script>
vendor: 1 bytes, line 328
328
329<script src="https://cdnjs.cloudflare.com/ajax/libs/mdbootstrap/4.19.1/js/mdb.min.js" integrity="sha512-Mug9KHKmroQFMLm93zGrjhibM2z2Obg9l6qFG2qKjXEXkMp/VDkI4uju9m4QKPjWSwQ6O2qzZEnJDEeCw0Blcw==" crossorigin="anonymous"></script>
329 330 331 332<!-- Mansory & imagesLoaded -->
333<script defer src="https://unpkg.com/masonry-layout@4/dist/masonry.pkgd.min.js"></script>
vendor: 1 bytes, line 333
333
334<script defer src="https://unpkg.com/imagesloaded@4/imagesloaded.pkgd.min.js"></script>
vendor: 1 bytes, line 334
334
335<script defer src="/assets/js/mansory.js" type="text/javascript"></script>
335 336 337 338 339 340 341<!-- Medium Zoom JS -->
342<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/medium-zoom.min.js" integrity="sha256-EdPgYcPk/IIrw7FYeuJQexva49pVRZNmt3LculEr7zM=" crossorigin="anonymous"></script>
vendor: 1 bytes, line 342
342
343<script src="/assets/js/zoom.js"></script>
343 344 345 346<!-- Load Common JS -->
347<script src="/assets/js/common.js"></script>
347 348 349 350<!-- MathJax -->
351<script type="text/javascript"> 352 window.MathJax = { 353 tex: { 354 tags: 'ams' 355 } 356 }; 357</script>
vendor: 1 bytes, line 357
357
358<script defer type="text/javascript" id="MathJax-script" src="https://cdn.jsdelivr.net/npm/[email protected]/es5/tex-mml-chtml.js"></script>
vendor: 1 bytes, line 358
358
359<script defer src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>
359 360 361 362 363<!-- Global site tag (gtag.js) - Google Analytics -->
vendor: 64 bytes, lines 363-364
363 364<script async src="https://www.googletagmanager.com/gtag/js?id=
364UA-130294541-1
vendor: 12 bytes, line 364
364"></script>
365<script> 366
vendor: 137 bytes, lines 366-370
366window.dataLayer = window.dataLayer || []; 367 function gtag() { dataLayer.push(arguments); } 368 gtag('js', new Date()); 369 370 gtag('config', '
370UA-130294541-1
vendor: 4 bytes, line 370
370');
371</script>
371 372 373 374<!-- Panelbear Analytics - We respect your privacy -->
375<script async src="https://cdn.panelbear.com/analytics.js?site=56zryTTuggW"></script>
vendor: 1 bytes, line 375
375
376<script> 377 window.panelbear = window.panelbear || function() { (window.panelbear.q = window.panelbear.q || []).push(arguments); }; 378 panelbear('config', { site: '56zryTTuggW' }); 379</script>
379 380 381 382 383 384 385</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.