<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8">
<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta name=Generator content="Microsoft Word 15 (filtered medium)"><!--[if !mso]><style>v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style><![endif]--><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:"Microsoft YaHei Light";
panose-1:2 11 5 2 4 2 4 2 2 3;}
@font-face
{font-family:"\@Microsoft YaHei Light";}
@font-face
{font-family:"MS PGothic";
panose-1:2 11 6 0 7 2 5 8 2 4;}
@font-face
{font-family:"\@MS PGothic";}
@font-face
{font-family:Mallory;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
h1
{mso-style-priority:9;
mso-style-link:"Heading 1 Char";
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:24.0pt;
font-family:"Calibri",sans-serif;
font-weight:bold;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri",sans-serif;
color:windowtext;}
span.Heading1Char
{mso-style-name:"Heading 1 Char";
mso-style-priority:9;
mso-style-link:"Heading 1";
font-family:"Calibri",sans-serif;
font-weight:bold;}
span.odd
{mso-style-name:odd;}
span.date-display-single
{mso-style-name:date-display-single;}
span.date-display-range
{mso-style-name:date-display-range;}
span.date-display-start
{mso-style-name:date-display-start;}
span.date-display-end
{mso-style-name:date-display-end;}
.MsoChpDefault
{mso-style-type:export-only;
font-family:"Calibri",sans-serif;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:1055739835;
mso-list-template-ids:-348615884;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level2
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:1.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:1.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:2.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level5
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:2.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:3.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:3.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level8
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:4.0in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:4.5in;
mso-level-number-position:left;
text-indent:-.25in;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
ol
{margin-bottom:0in;}
ul
{margin-bottom:0in;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1027" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-US link="#0563C1" vlink="#954F72" style='word-wrap:break-word'><div class=WordSection1><p class=MsoNormal style='background:white'><span style='color:#073763;mso-fareast-language:JA'><img width=115 height=37 style='width:1.1979in;height:.3854in' id="Picture_x0020_3" src="cid:image001.png@01D8233D.621DD890" alt="Department of Statistics and Data Science
"></span><span style='font-family:"Microsoft YaHei Light",sans-serif;color:#073763;mso-fareast-language:JA'> <a href="https://statistics.yale.edu/" target="_blank" title=Home><span style='font-size:22.0pt;color:#0563C1'>Department of Statistics and Data Science </span></a></span><i><span style='font-size:22.0pt;font-family:"Microsoft YaHei Light",sans-serif;color:#073763;mso-fareast-language:JA'> </span></i><span style='font-family:"Microsoft YaHei Light",sans-serif;mso-fareast-language:JA'><o:p></o:p></span></p><h1 style='mso-margin-top-alt:.1in;margin-right:0in;margin-bottom:0in;margin-left:0in;background:white'><span style='font-size:23.0pt;font-family:Mallory;color:#003C76;text-transform:uppercase;font-weight:normal'>YANG SONG</span><span style='font-size:13.0pt;font-family:Mallory;color:#222222'>, </span><span class=odd><span style='font-size:13.0pt;font-family:Mallory;color:#222222'>Stanford University</span></span><span style='font-size:13.0pt;font-family:Mallory;color:#222222;font-weight:normal'><o:p></o:p></span></h1><p class=MsoNormal style='background:white'><!--[if gte vml 1]><v:shapetype id="_x0000_t75" coordsize="21600,21600" o:spt="75" o:preferrelative="t" path="m@4@5l@4@11@9@11@9@5xe" filled="f" stroked="f">
<v:stroke joinstyle="miter" />
<v:formulas>
<v:f eqn="if lineDrawn pixelLineWidth 0" />
<v:f eqn="sum @0 1 0" />
<v:f eqn="sum 0 0 @1" />
<v:f eqn="prod @2 1 2" />
<v:f eqn="prod @3 21600 pixelWidth" />
<v:f eqn="prod @3 21600 pixelHeight" />
<v:f eqn="sum @0 0 1" />
<v:f eqn="prod @6 1 2" />
<v:f eqn="prod @7 21600 pixelWidth" />
<v:f eqn="sum @8 21600 0" />
<v:f eqn="prod @7 21600 pixelHeight" />
<v:f eqn="sum @10 21600 0" />
</v:formulas>
<v:path o:extrusionok="f" gradientshapeok="t" o:connecttype="rect" />
<o:lock v:ext="edit" aspectratio="t" />
</v:shapetype><v:shape id="Picture_x0020_3" o:spid="_x0000_s1026" type="#_x0000_t75" style='position:absolute;margin-left:0;margin-top:.35pt;width:87.5pt;height:105pt;z-index:251658240;visibility:visible;mso-wrap-style:square;mso-width-percent:0;mso-height-percent:0;mso-wrap-distance-left:9pt;mso-wrap-distance-top:0;mso-wrap-distance-right:9pt;mso-wrap-distance-bottom:0;mso-position-horizontal:absolute;mso-position-horizontal-relative:text;mso-position-vertical:absolute;mso-position-vertical-relative:text;mso-width-percent:0;mso-height-percent:0;mso-width-relative:page;mso-height-relative:page'>
<v:imagedata src="cid:image003.jpg@01D8233D.C726B6D0" o:title="" />
<w:wrap type="square"/>
</v:shape><![endif]--><![if !vml]><img width=117 height=140 style='width:1.2187in;height:1.4583in' src="cid:image002.jpg@01D8233E.276F26D0" align=left hspace=12 v:shapes="Picture_x0020_3"><![endif]><span class=date-display-single><span style='font-size:13.5pt;font-family:Mallory;color:#003C76'>Monday, February 21, 2022<o:p></o:p></span></span></p><p class=MsoNormal style='background:white'><span class=date-display-start><span style='font-size:13.5pt;font-family:Mallory;color:#003C76'>4:00PM</span></span><span class=date-display-range><span style='font-size:13.5pt;font-family:Mallory;color:#003C76'> to </span></span><span class=date-display-end><span style='font-size:13.5pt;font-family:Mallory;color:#003C76'>5:00PM</span></span><span style='font-size:13.0pt;font-family:Mallory;color:#222222'><o:p></o:p></span></p><p class=MsoNormal style='background:white'><span style='font-size:13.0pt;font-family:Mallory;color:#222222'>Zoom: <a href="https://yale.zoom.us/j/92366427609">https://yale.zoom.us/j/92366427609</a><o:p></o:p></span></p><p class=MsoNormal style='background:white'><span style='font-size:13.0pt;font-family:Mallory;color:#222222'><a href="https://yang-song.github.io/"><span style='font-size:12.0pt;color:#003C76'>Website</span></a><o:p></o:p></span></p><p class=MsoNormal style='background:white'><b><span style='font-size:15.0pt;font-family:Mallory;color:#222222'><o:p> </o:p></span></b></p><p class=MsoNormal style='background:white'><b><span style='font-size:15.0pt;font-family:Mallory;color:#222222'><o:p> </o:p></span></b></p><p class=MsoNormal style='background:white'><b><span style='font-size:15.0pt;font-family:Mallory;color:#222222'>Title: Learning to Generate Data by Estimating Gradients of the Data Distribution<o:p></o:p></span></b></p><p class=MsoNormal style='background:white'><span style='font-size:13.0pt;font-family:Mallory;color:#222222'><o:p> </o:p></span></p><p class=MsoNormal style='background:white'><b><span style='font-size:13.0pt;font-family:Mallory;color:#222222'>Information and Abstract: <o:p></o:p></span></b></p><p style='mso-margin-top-alt:0in;margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing: inherit'><span style='font-size:13.0pt;font-family:Mallory;color:#222222'> Generating data with complex patterns, such as images, audio, and molecular structures, requires fitting very flexible statistical models to the data distribution. Even in the age of deep neural networks, building such models is difficult because they typically require an intractable normalization procedure to represent a probability distribution. To address this challenge, I propose to model the vector field of gradients of the data distribution (known as the score function), which does not require normalization and therefore can take full advantage of the flexibility of deep neural networks. I will show how to (1) estimate the score function from data with flexible deep neural networks and principled statistical methods, (2) generate new data using stochastic differential equations and Markov chain Monte Carlo, and even (3) evaluate probabilities as in a traditional statistical model. The resulting method, called score-based generative modeling, achieves record-breaking performance in applications including image synthesis, text-to-speech generation, time series prediction, and point cloud generation, challenging the long-time dominance of generative adversarial networks (GANs) on many of these tasks. Furthermore, unlike GANs, score-based generative models are suitable for Bayesian reasoning tasks such as solving ill-posed inverse problems, and I have demonstrated their superior performance on examples like sparse-view computed tomography and accelerated magnetic resonance imaging. Finally, I will discuss how score-based generative modeling opens up new opportunities and new future research directions for building better machines to create and understand complex data in various disciplines of science and engineering.<o:p></o:p></span></p><p style='mso-margin-top-alt:0in;margin-right:0in;margin-bottom:12.0pt;margin-left:0in;background:white;box-sizing: inherit'><strong><span style='font-size:13.0pt;font-family:Mallory;color:#222222'>Bio: </span></strong><span style='font-size:13.0pt;font-family:Mallory;color:#222222'>Yang Song is a final year Ph.D. student at Stanford University. His research interest is in deep generative models and their applications to inverse problem solving and AI safety. His first-author papers have been recognized with an Outstanding Paper Award at ICLR-2021, and an oral presentation at NeurIPS-2019. He is a recipient of the Apple PhD Fellowship in AI/ML, the J.P. Morgan PhD Fellowship, and the WAIC Rising Star Award.<o:p></o:p></span></p><p class=MsoNormal><span style='mso-fareast-language:JA'><o:p> </o:p></span></p><p class=MsoNormal><o:p> </o:p></p></div></body></html>