Select a calendar:
Filter April Events by Event Type:
Events for April 25, 2023
-
PhD Thesis Defense - Yannan Li
Tue, Apr 25, 2023 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Defense - Yannan Li
Title: Formal Analysis of the Data Poisoning Robustness of K-Nearest Neighbors
Committee members(Lexicographic order): Pierluigi Nuzzo, Mukund Raghothaman, Chao Wang (chair)
Abstract: Data poisoning, which aims to corrupt a machine learning model and change its inference results by changing data elements in its training set, poses a significant threat to machine learning based software systems. However, formally certifying data poisoning robustness is a challenging task. I designed and implemented a set of formal methods for deciding, both efficiently and accurately, the data-poisoning robustness of the k-nearest neighbors (KNN) algorithm, which is a widely-used supervised machine learning technique. First, I developed a method for certifying the data-poisoning robustness of KNN by soundly overapproximating both the learning and inference phases of the KNN algorithm. Second, I developed a method for falsifying data-poisoning robustness, by quickly detecting the truly-non-robust cases using search space pruning and sampling. Finally, I extended these methods to other attack models and fairness certification, thus allowing for a more comprehensive analysis of the robustness of KNN.
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/94891715635?pwd=SFI5VFBtMndhN3BORk5GSjRyS2IzQT09
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
-
PhD Thesis Proposal - Shihan Lu
Tue, Apr 25, 2023 @ 11:00 AM - 01:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Analysis, Synthesis, and Perception of Multimodal Feedback for Humans and Robots
Committee: Heather Culbertson (Chair), Stefanos Nikolaidis, Gaurav Sukhatme, Jernej Barbic, Shrikanth Narayanan
Date: Tuesday, April 25, 11 am - 1 pm PST
Abstract: Multimodal feedback, including haptic and auditory feedback, is often overlooked in interactive and contact-rich scenarios in the studies with both humans and robots, such as writing on the back of an envelope with a pen or grasping a block in a Jenga game. In this work, I focus on three perspectives related to the multimodal feedback in interactions: (1) Analysis â“ how to extract useful and interpretable features from multimodal feedback; (2) Synthesis â“ how to simulate realistic virtual feedback; and (3) Perception â“ how humans and robots respond to the feedback. I explore these perspectives through tasks of sound modeling, haptic texture design, large-scale texture classification, and state-aware robot manipulation. With these tasks, the objective is to enhance the interactive experience in virtual reality, improve the understanding of crossmodal relationships, and complement visual and tactile sensing in challenging robot manipulation tasks.
Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CS Colloquium: Wanrong Zhang (Harvard) - Enabling Interactivity to Move Differential Privacy Closer to Practice
Tue, Apr 25, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Wanrong Zhang, Harvard University
Talk Title: Enabling Interactivity to Move Differential Privacy Closer to Practice
Series: CS Colloquium
Abstract: With growing concerns about large-scale data collection and surveillance, the development of privacy-preserving tools can help alleviate public fears about the misuse of personal data. The field of differential privacy (DP) offers powerful data analysis tools that provide worst-case privacy guarantees. However, most of the existing tools in the differential privacy literature only apply to static databases with non-interactive analysis, which release query answers in a single shot. In practice, data analysts often need to perform a sequence of adaptive analyses on data arriving online, which raises the need for interactive data analysis. This development poses two major questions: 1. How can we design interactive mechanisms that strike a better trade-off between privacy and accuracy? 2. Can we combine multiple interactive mechanisms as building blocks to create a more complex DP algorithm?
In this talk, I will discuss some of my work that answers these questions. To answer the first question, I have created a wide set of tools for private online decision-making problems. I will present one example problem for handling online databases---differentially private change-point detection. Second, I will show the optimal composition theorems for composing multiple interactive mechanisms. My work is among the first to address this long-standing gap in the understanding of composition for differential privacy. I will conclude the talk with my future directions.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Wanrong Zhang is an NSF Computing Innovation Fellow in the Theory of Computing group at Harvard John A. Paulson School of Engineering and Applied Sciences. She is also a member of the Harvard Privacy Tools/OpenDP project. Her primary focus is to address new challenges introduced by real-world deployments of differential privacy. Before joining Harvard, she received her Ph.D. from Georgia Institute of Technology. She was selected as a rising star in EECS in 2022 and a rising star in Data Science in 2021. She is a recipient of the Computing Innovation Fellowship from CCC/CRA/NSF.
Host: Jiapeng Zhang
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
PHD Thesis Proposal - Woojeong Jin
Tue, Apr 25, 2023 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
PHD Thesis Proposal - Woojeong Jin
Title: Towards a Better Reasoner on Visual Information
Humans acquire knowledge by processing visual information through observation and imagination, which expands our reasoning capability about the physical world we encounter every day. Despite significant progress in solving AI problems, current state-of-the-art models in natural language processing (NLP) and computer vision (CV) have limitations in terms of reasoning and generalization, particularly with complex reasoning on visual information and generalizing to unseen vision-language tasks. This thesis proposal aims to address these shortcomings by presenting a series of works that enable smaller vision-language (VL) models to generalize to new tasks, improve language models by incorporating visual information, and evaluate language models by assessing their ability to reason about the physical world through text.
https://usc.zoom.us/j/98941948220
12 pm on 4/25
Committee Members: Xiang Ren, Ram Nevatia, Jesse Thomason, Robin Jia, Emilio Ferrara.Location: https://usc.zoom.us/j/98941948220
Audiences: Everyone Is Invited
Contact: Asiroh Cham
Event Link: https://usc.zoom.us/j/98941948220
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
PHD Thesis Proposal - Peifeng Wang
Tue, Apr 25, 2023 @ 03:00 PM - 04:30 PM
Thomas Lord Department of Computer Science
University Calendar
PHD Thesis Proposal - Peifeng Wang
Title: Building Small-Scale but Advanced Language Reasoners
Abstract:
The entanglement of multiple language capabilities within large language models requires expensive scaling to work effectively. I argue that a disassociation of these capabilities from core language skills can enable the creation of smaller, more accessible language models. Additionally, this disassociation will facilitate the development of language models with enhanced reasoning abilities.
This thesis proposal presents three techniques to build small language models with advanced reasoning capabilities. First, I introduce an Imagine&Verbalize framework for generative commonsense reasoning, which decomposes a complex generation task into easier sub-tasks and learns from a diverse set of indirect supervision from multiple domains. Second, I present a knowledge-transferring pipeline which prompts large language models to rationalize for an open-domain question and then trains small language models to answer consistently. Third, I discuss augmenting small LMs with a working memory for coherent language reasoning by tracking the states of the described world.
Venue: zoom at https://usc.zoom.us/j/97850702935?pwd=ekJ0K1RMM045Tk1EQUV1OUEvOE5iQT09
Date and time: 3:00pm-4:30pm on April 25th
Committee Members: Xiang Ren (chair), Filip Ilievski, Swabha Swayamdipta, Ram Nevatia, Emilio Ferrara
Location: https://usc.zoom.us/j/97850702935?pwd=ekJ0K1RMM045Tk1EQUV1OUEvOE5iQT09
Audiences: Everyone Is Invited
Contact: Asiroh Cham
Event Link: https://usc.zoom.us/j/97850702935?pwd=ekJ0K1RMM045Tk1EQUV1OUEvOE5iQT09
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CS Colloquium: Silvia Sellan (University of Toronto) - "Geometry +": A Tour of Geometry Processing Research
Tue, Apr 25, 2023 @ 04:00 PM - 05:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Silvia Sellan, University of Toronto
Talk Title: "Geometry +": A Tour of Geometry Processing Research
Series: CS Colloquium
Abstract: From virtual reality to 3D printing, all the way through self-driving cars and the metaverse, today's technological advances rely more and more on capturing, creating and processing three-dimensional geometry. In this talk, we will show how geometry processing can empower other areas of Computer Science to find new research questions and solutions. Specifically, we will focus on our latest progress on realtime fracture simulation for video games, an algorithmic fairness analysis of gender in the Computer Graphics literature and a quantification of the uncertainty associated with several steps of the Geometry Processing pipeline
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Silvia is a fourth year Computer Science PhD student at the University of Toronto. She is advised by Alec Jacobson and working in Computer Graphics and Geometry Processing. She is a Vanier Doctoral Scholar, an Adobe Research Fellow and the winner of the 2021 University of Toronto Arts & Science Dean's Doctoral Excellence Scholarship. She has interned twice at Adobe Research and twice at the Fields Institute of Mathematics. She is also a founder and organizer of the Toronto Geometry Colloquium and a member of WiGRAPH. She is currently looking to survey potential future postdoc and faculty positions, starting Fall 2024
Host: Oded Stein
Location: Seeley G. Mudd Building (SGM) - 124
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
