Past events

Current undergraduate students are invited to attend a virtual information session about the Computer Science & Engineering Integrated Program.

This is an integrated Bachelor's and Master's Degree program that allows students to take credits at the undergraduate tuition rate to be applied towards the Computer Science M.S. program.  

We'll briefly discuss the program, the application process, and why you might want to pursue a graduate degree. The majority of the time will be dedicated to questions and answers with program staff!

If you plan on attending, please RSVP HERE.

The last day to cancel full semester classes and not receive a "W" is Monday, February 1. This is also the last day to receive a 75% tuition refund for canceling full semester classes.

In addition, this is the last day to add classes without college approval and to change grade basis (A-F or S/N) for full semester classes.

View the full academic schedule on One Stop.

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m.

This week's speaker, Hongyang Zhang (Toyota Technological Institute at Chicago), will be giving a talk titled "New Advances in (Adversarially) Robust and Secure Machine Learning".

Abstract

Deep learning models are often vulnerable to adversarial examples. In this talk, we will focus on robustness and security of machine learning against adversarial examples. There are two types of defenses against such attacks: 1) empirical and 2) certified adversarial robustness.

In the first part of the talk, we will see the foundation of our winning system, TRADES, in the NeurIPS’18 Adversarial Vision Challenge in which we won 1st place out of 400 teams and 3,000 submissions. Our study is motivated by an intrinsic trade-off between robustness and accuracy: we provide a differentiable and tight surrogate loss for the trade-off using the theory of classification-calibrated loss. TRADES has record-breaking performance in various standard benchmarks and challenges, including the adversarial benchmark RobustBench, the NLP benchmark GLUE, the Unrestricted Adversarial Examples Challenge hosted by Google, and has motivated many new attacking methods powered by our TRADES benchmark.

In the second part of the talk, to equip empirical robustness with certification, we study certified adversarial robustness by random smoothing in the L_infty threat model. On one hand, we show that random smoothing on the TRADES-trained classifier achieves SOTA certified robustness when the L_infty perturbation radius is small. On the other hand, when the perturbation is large, i.e., independent of inverse of input dimension, we show that random smoothing is provably unable to certify L_infty robustness for arbitrary random noise distribution. The intuition behind our theory reveals an intrinsic difficulty of achieving certified robustness by “random noise based methods”, and inspires new directions as potential future work.

Biography

Hongyang Zhang is a Postdoc fellow at Toyota Technological Institute at Chicago, hosted by Avrim Blum and Greg Shakhnarovich. He obtained his Ph.D. from CMU Machine Learning Department in 2019, advised by Maria-Florina Balcan and David P. Woodruff. His research interests lie in the intersection between theory and practice of machine learning, robustness and AI security. His methods won the championship or ranked top in various competitions such as the NeurIPS’18 Adversarial Vision Challenge (all three tracks), the Unrestricted Adversarial Examples Challenge hosted by Google, and the NeurIPS’20 Challenge on Predicting Generalization of Deep Learning. He also authored a book in 2017.

Prospective students can RSVP for an information session to learn about the following graduate programs:

• Computer Science M.S.
• Computer Science MCS
• Computer Science Ph.D.
• Data Science M.S.
• Data Science Post-Baccalaureate Certificate

During the information session, we will go over the following:

• Requirements (general)
• Applying
• Prerequisite requirements
• What makes a strong applicant
• Funding
• Resources
• Common questions
• Questions from attendees

The last day to receive a 100% tuition refund for canceling full semester classes is Monday, January 25.

This is also the last day to add full semester classes without instructor approval.

View the full academic schedule on One Stop.

The computer science colloquium takes place on Mondays from 11:15 a.m. - 12:15 p.m.

This week's talk is part of the Cray Distinguished Speaker Series. This series was established in 1981 by an endowment from Cray Research and brings distinguished visitors to the Department of Computer Science & Engineering every year. 

This week's speaker is Miryung Kim from the University of California, Los Angeles.

Abstract

We are at an inflection point where software engineering meets the data-centric world of big data, machine learning, and artificial intelligence.   As software development gradually shifts to the development of data analytics with AI and ML technologies, existing software engineering techniques must be re-imagined to provide the productivity gains that developers desire. We conducted a large scale study of almost 800 professional data scientists in the software industry to investigate what a data scientist is, what data scientists do, and what challenges they face. This study has found that ensuring correctness is a huge problem in data analytics.

We argue for re-targeting software engineering research to address new challenges in the era of data-centric software development. We showcase a few examples of my group's research on debugging and testing of data-intensive applications: e.g., data provenance, symbolic-execution based test generation, and fuzz testing in Apache Spark. We then conclude with open problems in software engineering to meet the needs of AI and ML workforce.

Biography

Miryung Kim is a Full Professor in the Department of Computer Science at the University of California, Los Angeles. She is known for her research on code clones---code duplication detection, management, and removal solutions. Recently, she has taken a leadership role in defining the emerging area of software engineering for data science. She received her B.S. in Computer Science from Korea Advanced Institute of Science and Technology and her M.S. and Ph.D. in Computer Science and Engineering from the University of Washington.  She received various awards including an NSF CAREER award, Google Faculty Research Award, Okawa Foundation Research Award, and Alexander von Humboldt Foundation Fellowship. She was previously an assistant professor at the University of Texas at Austin and also spent time as a visiting researcher at Microsoft Research. She is the lead organizer of a Dagstuhl Seminar on SE4ML---Software Engineering for AI-ML based Systems. She is a Keynote Speaker at ASE 2019, a Program Co-Chair of ESEC/FSE 2022, and an Associate Editor of IEEE Transactions on Software Engineering.

Welcome back! The spring 2021 semester begins on Tuesday, January 19.

View the full academic schedule on One Stop.

The University of Minnesota will be closed in observance of Martin Luther King, Jr. Day.

View the full schedule of University holidays.
 

Data matters! That’s the theme for this year’s UMN Day of Data, which explores the ways that data is used to address local and global issues including racial justice, epidemiology/health, climate, privacy and more. The event is open to all students, faculty, staff, and alumni from all University of Minnesota campuses, and attendance is free. Participants are invited to attend as many or few sessions as you like. All sessions will take place virtually.

Wednesday, January 13 - Friday, January 15
Morning session: 10:00 a.m. - 12:00 p.m.
Afternoon session: 1:00 p.m. - 3:00 p.m.

The University of Minnesota will be closed for New Year's Day.

View the full schedule of University holidays.