<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div>
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<div dir="ltr">
<table align="center" bgcolor="#fff" border="0" cellpadding="0" cellspacing="0" width="600" style="font-family:Arial,sans-serif">
<tbody>
<tr>
<td><img alt="Dissertation Defense Announcement at the Cullen College of Engineering" width="600" height="171" src="https://www.egr.uh.edu/sites/www.egr.uh.edu/files/enews/2022/images/dissertation1.png">
<table align="center" bgcolor="#ffffff" border="0" cellpadding="10" cellspacing="0">
<tbody>
<tr>
<td align="center" style="padding:40px 20px 10px">
<div style="line-height:28px"><font color="#c8102e"><span style="font-size:24px"><b>Towards Plausible Collaborative Machine Learning: Privacy, Efficiency and Fairness</b></span></font><br>
</div>
<div style="margin-top:5px; line-height:22px"><br>
</div>
<div style="margin:30px 0px; line-height:20px">
<div style="font-size:18px; margin-bottom:5px"><strong>Jiahao Ding</strong></div>
<div style="line-height:20px">
<p style="line-height:22px; margin:0px 0px 5px"><font face="Arial, Helvetica, sans-serif"><span style="font-size:14px">April 22, 2022; 10:00 AM - 12:00 PM (CST)</span></font><br>
<font face="Arial, Helvetica, sans-serif"><span style="font-size:14px">Location: Zoom Meeting</span></font><br>
<font face="Arial, Helvetica, sans-serif"><span style="font-size:14px">Zoom: </span></font><font color="#c8102e" face="Arial, Helvetica, sans-serif"><span style="font-size:14px"><u><a href="https://urldefense.com/v3/__https://uh-edu-cougarnet.zoom.us/j/9167221115__;!!LkSTlj0I!AYHlDOrfeq1r2lXCGKYp75YmD6rrKcmFd29Xzwtyxxwme4lK4dR4OZ0MtER5z6igMyUIrOakxS8f7g9HNYf_TA$" data-auth="NotApplicable">https://uh-edu-cougarnet.zoom.us/j/9167221115</a></u></span></font></p>
</div>
</div>
<div style="font-size:14px; line-height:20px">
<p style="font-family:Arial,Helvetica,sans-serif; line-height:22px; margin:0px 0px 5px">
<strong>Committee Chair:</strong><br>
Miao Pan, Ph.D.<br>
</p>
</div>
<div style="font-size:14px; line-height:20px">
<p style="font-family:Arial,Helvetica,sans-serif; line-height:22px; margin:0px 0px 20px">
<strong>Committee Members:</strong><br>
Zhu Han, Ph.D. | Hien Van Nguyen, Ph.D. | Xin Fu, Ph.D. | Yanmin Gong, Ph.D.</p>
</div>
</td>
</tr>
<tr>
<td style="padding:0px 20px 20px">
<p style="font-family:Arial,Helvetica,sans-serif; font-size:16px; line-height:22px; margin:15px 0px; color:rgb(200,16,46)">
<strong>Abstract</strong></p>
<p style="line-height:22px; margin:15px 0px"><font face="Arial, Helvetica, sans-serif"><span style="font-size:14px">Nowadays, the development of machine learning shows great potential in a variety of fields, such as retail, healthcare, and insurance. Effective
machine learning models can automatically learn useful information from a large amount of data and provide decisions with high average accuracy. Although machine learning has infiltrated into many areas due to its advantages, a vast amount of data has been
generated at an ever-increasing rate, which leads to significant computational complexity for data collection and processing via a centralized machine learning approach. Distributed machine learning thus has received huge interest due to its capability of
exploiting the collective computing power of edge devices. However, during the learning process, model updates using local private samples and large-scale parameter exchanges among agents impose severe privacy concerns and communication bottlenecks. Moreover,
the decisions and predictions offered by the learning models may cause certain fairness concerns among population groups of interest, when the grouping is based on such sensitive attributes as race and gender. </span></font></p>
<p style="line-height:22px; margin:15px 0px"><span style="font-size:14px; font-family:Arial,Helvetica,sans-serif">To address those challenges, in this dissertation, we first propose a number of differentially private Alternating Direction Method of Multipliers
(ADMM) algorithms that leverage two key ideas to balance the privacy-accuracy tradeoff: (1) adding Gaussian noise with decaying variance to reduce the negative effects of noise addition and maintain the convergence behaviors; and (2) outputting a noisy approximate
solution for the perturbed objective to release the shackles of the exact optimal solution during each ADMM iteration to ensure DP. It is shown that our algorithms can significantly improve the privacy-accuracy tradeoff over existing solutions. Second, we
develop a differentially private and communication efficient decentralized gradient descent method that will update the local models by integrating DP noise and random quantization operator to simultaneously enforce DP and communication efficiency. Finally,
we focus on addressing the discrimination and privacy concerns in classification models by incorporating functional mechanism and decision boundary covariance, a novel measure of decision boundary fairness.</span></p>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
<tr>
<td><img alt="Engineered For What's Next" width="600" height="82" src="https://www.egr.uh.edu/sites/www.egr.uh.edu/files/enews/2022/images/dissertation2.png"></td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</body>
</html>