Fwd: RI Ph.D. Thesis Defense: Jack Good

[Artur Dubrawski]

Please mark your calendars to attend this transformative event!

Cheers
Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Mon, Oct 14, 2024 at 11:06 AM
Subject: RI Ph.D. Thesis Defense: Jack Good
To: RI People <ri-people at andrew.cmu.edu>


*Date:* 23 October 2024
*Time:* 3:30 p.m. (ET)
*Location:* GHC 6501
*Zoom Link:*
https://cmu.zoom.us/j/98137707124?pwd=g1OvJBlbgfZFtLQm3tIaEWos9eFhcZ.1
*Type:* Ph.D. Thesis Defense
*Who:* Jack Good
*Title:* Trustworthy Learning using Uncertain Interpretation of Data

*Abstract:*
Motivated by the potential of Artificial Intelligence (AI) in high-cost and
safety-critical
applications, and recently also by the increasing presence of AI in our
everyday lives, Trustworthy AI has grown in prominence as a broad area of
research encompassing topics such as interpretability, robustness,
verifiable safety, fairness, privacy, accountability, and more. This has
created a tension between simple, transparent models with inherent
trust-related benefits and complex, black-box models with unparalleled
performance on many tasks. Towards closing this gap, we propose and study
an uncertain interpretation of numerical data and apply it to tree-based
models, resulting in a novel kind of fuzzy decision tree called Kernel
Density Decision Trees (KDDTs) with improved performance, enhanced
trustworthy qualities, and increased utility, enabling the use of these
trees in broader applications. We group the contributions of this thesis
into three pillars.

The first pillar is robustness and verification. The uncertain
interpretation, by accounting for uncertainty in the data, and more
generally as a kind of regularization on the function represented by a
model, can improve the model with respect to various notions of robustness.
We demonstrate its ability to improve robustness to noisy features and
noisy labels, both of which are common in real-world data. Next, we show
how efficiently verifiable adversarial robustness is achievable through the
theory of randomized smoothing. Finally, we discuss the related topic of
verification and propose the first verification algorithm for fuzzy
decision trees.

The second pillar is interpretability. While decision trees are widely
considered to be interpretable, good performance from tree-based models is
often limited to tabular data and demands both feature engineering, which
increases design effort, and ensemble methods, which severely diminish
interpretability compared to single-tree models. By leveraging the
efficient fitting and differentiability of KDDTs, we propose a system of
learning parameterized feature transformations for decision trees. By
choosing interpretable feature classes and applying sparsity
regularization,we can obtain compact single-tree models with competitive
performance. We demonstrate application to tabular, time series, and simple
image data.

The third pillar is pragmatic advancements. Semi-supervised Learning (SSL)
is motivated by the expense of labeling and learns from a mix of labeled
and unlabeled data. SSL for trees is generally limited to black-box wrapper
methods, for which trees are not well-suited. We propose as an alternative
a novel intrinsic SSL method based on our uncertain interpretation of data.
Federated Learning (FL) is motivated by data sharing limitations and learns
from distributed data by communicating models. We introduce a new FL
algorithm based on function space regularization, which borrows concepts
and methods from our formalism of uncertain interpretation. Unlike prior FL
methods, it supports non-parametric models and has convergence guarantees
under mild assumptions. Finally, we show how our FL algorithm also provides
a simple utility for ensemble merging.

*Thesis Committee Members:*
Artur Dubrawski, Chair
Jeff Schneider
Tom Mitchell
Gilles Clermont, University of Pittsburgh

A draft of the thesis defense document is available here
<https://drive.google.com/file/d/1q2Iy7KGQ8LvgrII71d1kLUMXnBKU31BT/view?usp=sharing>
.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20241014/2ff449fd/attachment.html>