<div dir="ltr">And the details of Maria's defense on Monday:<div><br></div><div><p class="MsoNormal">Please join us on Monday, May 4 via Zoom at 11am when Maria De-Arteaga (ML & Public Policy Joint PhD) will be defending her thesis. </p><p class="MsoNormal"><b>Title:</b> Machine Learning in High-Stakes Settings: Risks and Opportunities</p><p class="MsoNormal"><b>Thesis committee:</b> Artur Dubrawski (Co-Chair), Alexandra Chouldechova (Co-Chair), Roni Rosenfeld, Adam Tauman Kalai (Microsoft Research)</p><p class="MsoNormal"><b>Zoom Link:</b> <a href="https://cmu.zoom.us/j/94967473449?pwd=b09lL29qblg1ZU5BWHZhVDB2NjFjQT09" target="_blank">https://cmu.zoom.us/j/94967473449?pwd=b09lL29qblg1ZU5BWHZhVDB2NjFjQT09</a></p><p class="MsoNormal" style="margin-bottom:12pt"><b>Meeting ID:</b> 949 6747 3449<br><b>Password:</b> 000312</p><p class="MsoNormal"><b>Abstract: </b> Machine learning (ML) is increasingly being used to support decision-making in critical settings, where predictions have potentially grave implications over human lives. Examples include healthcare, hiring, child welfare, and the criminal justice system. In this thesis, I study the risks and opportunities of machine learning in high-stakes settings. In the first chapter I focus on opportunities of ML to support experts' decisions when dealing with high-resolution multivariate data, a type of data that is particularly hard for humans to interpret. I propose methodology to discover latent complex multivariate correlation structures and illustrate its use in two different domains: (1) identification of radioactive threats in nuclear physics, and (2) prediction of neurological recovery of comatose patients in healthcare. In the second chapter, focused on algorithmic fairness, I demonstrate how societal biases encoded in historical data may be reproduced and amplified by ML models, and introduce a new algorithm to mitigate biases without assuming access to protected attributes. Finally, in the third chapter I characterize challenges that arise from the limitations of available labels in decision support contexts--such as the selective labels problem and omitted payoff bias--and propose methodology to estimate and leverage human consistency to improve algorithmic recommendations and human-machine complementarity.</p><p class="MsoNormal"><b> </b></p><b>Paper Link:</b> <a href="https://www.dropbox.com/s/h449z85r6nls8oc/Dissertation_DeArteaga.pdf?dl=0" target="_blank"><span style="color:windowtext">https://www.dropbox.com/s/h449z85r6nls8oc/Dissertation_DeArteaga.pdf?dl=0</span></a> </div><div> <br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, Apr 28, 2020 at 11:28 AM Artur Dubrawski <<a href="mailto:awd@cs.cmu.edu">awd@cs.cmu.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr">Dear Autonians,<div><br></div><div>Please join me in attending 2 (yes, two) excellent virtual presentations by our own Maria De-Arteaga and Chao Liu, both of which are scheduled for the next week.</div><div><br></div><div>(btw, I do not remember when was the last time we had more than one doctoral thesis defense scheduled in one week at the Auton Lab...)</div><div><br></div><div>Maria's defense will be on Monday May 4th at 11am, </div><div>The official announcement will be shared soon.<br><br>Chao's defense is scheduled for Thursday May 7th at noon.</div><div>The official announcement with the zoom link is included below.</div><div><br></div><div>Please help seeing these outstanding colleagues move to the next levels of their professional lives by attending these presentations and cheering for them :)</div><div><br></div><div>Cheers,</div><div>Artur</div><div><div class="gmail_quote"><div dir="ltr" class="gmail_attr"><br></div>-----<br>
<div dir="ltr">
<div id="gmail-m_3629644164193763502m_-3402725599274607738divtagdefaultwrapper" style="font-size:11pt;color:rgb(0,0,0);font-family:"Calibri Light","Helvetica Light",sans-serif" dir="ltr">
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont;font-size:11pt"><span style="font-size:11pt;font-family:"Calibri Light","Helvetica Light",sans-serif">Date: 07 May</span><span style="font-size:11pt;font-family:"Calibri Light","Helvetica Light",sans-serif"> 2020</span></span><span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Time: 12:00 p.m.</span><span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont;font-size:11pt"><span style="font-size:11pt;font-family:"Calibri Light","Helvetica Light",sans-serif">Place: *Virtual Presentation* </span></span><a href="https://cmu.zoom.us/j/2623852919" rel="noopener noreferrer" style="font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px" id="gmail-m_3629644164193763502m_-3402725599274607738LPlnk232672" target="_blank"><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">https://cmu.zoom.us/j/2623852919</span></a></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont;font-size:11pt"><span style="font-size:11pt"><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Type: Ph.D. Thesis</span><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt"> </span></span><span style="font-size:11pt;font-family:"Calibri Light","Helvetica Light",sans-serif">Defense</span></span><span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span></p>
<p style="margin:0in 0in 0.0001pt;font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont">
<span style="font-size:11pt;font-family:"Calibri Light","Helvetica Light",sans-serif">Who: </span><font face="Calibri Light, Helvetica Light, sans-serif, serif, EmojiFont"><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Chao
Liu</span></font></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Title: </span><span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span><span style="color:rgb(33,33,33);font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Vision
with Small Baselines</span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<br>
<span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Abstract:</span><span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span></p>
<div style="color:rgb(33,33,33);font-size:15px;font-family:arial,helvetica,sans-serif,serif,EmojiFont">
<div style="font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">3D sensing with portable imaging systems is becoming more and more popular in computer vision applications such as autonomous driving, virtual reality, robotics manipulation
and surveillance, due to the decreasing expense and size of RGB cameras. Despite the compactness and portability of the small baseline vision systems, it is well-known that the uncertainty in range finding using multiple views and the sensor baselines are
inversely related. On the other hand, besides compactness, the small baseline vision system has its unique advantages such as easier correspondence and large overlapping regions across views. </span><br>
<br>
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">The goal of this thesis is to develop computational methods and small baseline imaging systems for 3D sensing of complex scenes in real world conditions. Our design
principle is to physically model the scene complexities and specifically infer the uncertainties for the images captured with small baseline setups.</span><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt"> </span><br>
<br>
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">With this design principle, we make four contributions. In the first contribution, we propose a two-stage near-light photometric stereo method using a small (6 cm diameter)
LED ring. The imaging system is compact compared to traditional photometric stereo systems. In the second contribution, we develop an algorithm to simultaneously estimate the occlusion pattern and depth for thin structures from a focal image stack, which is
obtained either by varying the focus/aperture of the lens or computed from a one-shot light field image. As the third contribution, we propose a learning-based method to estimate per-pixel depth and its uncertainty continuously from a monocular video stream,
with small camera baselines across adjacent frames. These depth probability volumes are accumulated over time as more incoming frames are processed sequentially, which effectively reduces depth uncertainty and improves accuracy, robustness, and temporal stability.
Finally, using a pair of high resolution camera and laser projector, we develop a high spatial resolution Diffuse Optical Tomography (DOT) system that can detect accurate boundaries and relative depth of heterogeneous structures up to a depth of 8mm below
a highly scattering medium such as whole milk.</span></div>
<div style="font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont">
<br>
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">We showcase the application of a small baseline vision system for in-vivo micro-scale 3D reconstruction of capillary veins and develop a system for real-time analysis
of microvascular blood flow for critical care. We believe that the computational methods developed in this thesis would find more applications of compact 3D sensing under challenging conditions.</span></div>
</div>
<div style="color:rgb(33,33,33);font-size:15px;font-family:arial,helvetica,sans-serif,serif,EmojiFont">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont;font-size:11pt"></span></div>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt"> </span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Thesis Committee Members:</span><span style="font-family:Calibri,sans-serif,serif,EmojiFont"></span></p>
<p style="margin:0in 0in 0.0001pt;font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont">
<span style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px"><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Srinivasa
G. Narasimhan, Co-chai</span><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">r</span></span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px"><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Artur
W. Dubrawski, C</span><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">o-chair</span></span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Aswin C. Sankaranarayanan</span><br style="color:rgb(33,33,33);font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px">
<span style="color:rgb(33,33,33);font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">Manmohan Chandraker, </span><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">University
of California, San Diego</span><br>
</p>
<p style="margin:0in 0in 0.0001pt;font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont">
</p>
<p style="margin:0in 0in 0.0001pt;font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont">
<span style="font-size:11pt"></span></p>
<p style="margin:0in 0in 0.0001pt;font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont">
<font face="Calibri Light, Helvetica Light, sans-serif, serif, EmojiFont"></font></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont;font-size:11pt"><br>
</span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">A copy of the thesis document is available at:</span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif">
<a href="https://www.dropbox.com/s/cz75koh96ragy4x/thesis-small-baseline.pdf?dl=0" rel="noopener noreferrer" style="font-family:wf_segoe-ui_normal,"Segoe UI","Segoe WP",Tahoma,Arial,sans-serif,serif,EmojiFont;font-size:15px" id="gmail-m_3629644164193763502m_-3402725599274607738LPlnk545374" title="https://www.dropbox.com/s/cz75koh96ragy4x/thesis-small-baseline.pdf?dl=0
Cmd+Click or tap to follow the link" target="_blank"><span style="font-family:"Calibri Light","Helvetica Light",sans-serif;font-size:11pt">https://www.dropbox.com/s/cz75koh96ragy4x/thesis-small-baseline.pdf?dl=0</span></a><span style="font-family:"Calibri Light","Helvetica Light",sans-serif,serif,EmojiFont;font-size:11pt"><br>
</span></p>
<p style="margin:0in 0in 0.0001pt;font-size:medium;font-family:Calibri,sans-serif"><br></p></div></div>
</div></div></div>
</blockquote></div>