Past events

The UMN Machine Learning Seminar Series brings together faculty, students, and local industrial partners who are interested in the theoretical, computational, and applied aspects of machine learning, to pose problems, exchange ideas, and foster collaborations. The talks are every Thursday from 12 p.m. - 1 p.m. during the Fall 2021 semester.

This week's speaker, Uday V. Shanbhag (Penn State), will be giving a talk titled "Probability Maximization via Minkowski Functionals: Convex Representations and Tractable Resolution."

Abstract

In this paper, we consider the maximization of a probability P{ζ∣ζ∈K(x)} over a closed and convex set X, a special case of the chance-constrained optimization problem. We define K(x) as K(x)≜{ζ∈K∣c(x,ζ)≥0} where ζ is uniformly distributed on a convex and compact set K and c(x,ζ) is defined as either {c(x,ζ)≜1−|ζTx|m, m≥0} (Setting A) or c(x,ζ)≜Tx−ζ (Setting B). We show that in either setting, P{ζ∣ζ∈K(x)} can be expressed as the expectation of a suitably defined function F(x,ξ) with respect to an appropriately defined Gaussian density (or its variant), i.e. Ep~[F(x,ξ)]. We then develop a convex representation of the original problem requiring the minimization of g(E[F(x,ξ)]) over X where g is an appropriately defined smooth convex function. Traditional stochastic approximation schemes cannot contend with the minimization of g(E[F(⋅,ξ)]) over X, since conditionally unbiased sampled gradients are unavailable. We then develop a regularized variance-reduced stochastic approximation ({\textbf{r-VRSA}}) scheme that obviates the need for such unbiasedness by combining iterative {regularization} with variance-reduction. Notably, ({\textbf{r-VRSA}}) is characterized by both almost-sure convergence guarantees, a convergence rate of O(1/k1/2−a) in expected sub-optimality where a>0, and a sample complexity of O(1/ϵ6+δ) where δ>0.

Biography

Uday V. Shanbhag has held the Gary and Sheila Bello Chaired professorship in Ind. & Manuf. Engr. at Penn State University (PSU) since Nov. 2017 and has been at PSU since Fall 2012, prior to which he was at the University of Illinois at Urbana-Champaign (between 2006–2012, both as an assistant and a tenured associate professor). His interests lie in the analysis and solution of optimization problems, variational inequality problems, and noncooperative games complicated by nonsmoothness and uncertainty. He holds undergraduate and Master’s degrees from IIT,Mumbai (1993) and MIT, Cambridge (1998) respectively and a Ph.D. in management science and engineering (Operations Research) from Stanford University (2006).

Have all your questions about the Master of Science in Software Engineering (MSSE) program answered by attending this online information session.

RSVP now to reserve your spot.

Attendees will be sent a link prior to the event.
 

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 BIPOC Voices in STEM speaker series is free and open to students of all identities who are interested in or currently studying STEM at the University of Minnesota. The series highlights the experiences of UMN alumni who have current or past careers or degrees in STEM. Registration is required.

"Working at a Startup"
Pablo Garcia, co-founder of Crowd AI
Monday, October 11, 2021
6-7 p.m. Central Time
Register for the Zoom event
 

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

This week's speaker, Stephen McCamant (University of Minnesota), will be giving a talk titled "Symbolic Execution as a Flexible Tool for Binary Analysis."

Abstract

Analyzing software at the binary (machine code) level is advantageous or required in many scenarios, but it can be more challenging than source-level analysis because of the complexities of instruction sets and a lack of high-level structure. Symbolic execution is a very useful approach for building binary analyses because it encapsulates instruction-set complexity, does not require high-level structure, and serves as a foundation on which a variety of analyses can be built. I'll describe the open-source FuzzBALL system for binary symbolic execution we are developing at the University of Minnesota to discuss some design trade-offs. Then I'll briefly sketch three applications of binary symbolic execution. In test generation for security vulnerabilities, symbolic execution acts as an enhanced dynamic analysis. In enumerating the targets of jump tables, symbolic execution acts as a static analysis without conservative approximation.  And in generating tests for CPU emulators, it performs bounded-exhaustive enumeration.

Biography

Stephen McCamant is an Associate Professor of Computer Science and Engineering at the University of Minnesota, where he has been since the fall of 2012. His main research area is program analysis for software security and correctness. He is especially interested in binary code analysis and transformation, hybrid dynamic/static techniques and symbolic execution, information flow/taint analysis, and applications of decision procedures. His research on software-based fault isolation won the USENIX Security Test of Time award in 2018, and was adopted in Google's Native Client system. He received his Ph.D from the Massachusetts Institute of Technology in 2008, and from 2008-2012 he was a postdoc at UC Berkeley.

The UMN Machine Learning Seminar Series brings together faculty, students, and local industrial partners who are interested in the theoretical, computational, and applied aspects of machine learning, to pose problems, exchange ideas, and foster collaborations. The talks are every Thursday from 12 p.m. - 1 p.m. during the Fall 2021 semester.

This week's speaker, Eric Vanden-Eijnden (New York University), will be giving a talk titled "Machine Learning and Scientific Computing."

Abstract

The recent success of machine learning suggests that neural networks may be capable of approximating high-dimensional functions with controllably small errors. As a result, they could outperform standard function interpolation methods that have been the workhorses of current numerical methods. This feat offers exciting prospects for scientific computing, as it may allow us to solve problems in high-dimension once thought intractable. At the same time, looking at the tools of machine learning through the lens of applied mathematics and numerical analysis can give new insights as to why and when neural networks can beat the curse of dimensionality. I will briefly discuss these issues, and present some applications related to solving PDE in large dimensions and sampling high-dimensional probability distributions.

Biography

Eric Vanden-Eijnden is a Professor of Mathematics at the Courant Institute of Mathematical Sciences, New York University. His research focuses on the mathematical and computational aspects of statistical mechanics, with applications to complex dynamical systems arising in molecular dynamics, materials science, atmosphere-ocean science, fluids dynamics, and neural networks. He is also interested in the mathematical foundations of machine learning (ML) and the applications of ML in scientific computing. He is known for the development and analysis of multiscale numerical methods for systems whose dynamics span a wide range of spatio-temporal scales. He is the winner of the Germund Dahlquist Prize and the J.D. Crawford Prize, and a recipient of the Vannevar Bush Faculty Fellowship.

The last day to receive a 25% tuition refund for canceling full semester classes is Monday, October 4.

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, Hyun Soo Park (University of Minnesota), will be giving a talk titled "Self-supervised Behavioral Imaging."

Abstract

Nonverbal behavioral signals such as gaze direction, facial expression, and body gesture have been ingrained into our interpersonal communications, which often appear at microscopic scale. Despite their omnipresence in all aspects of social interactions, existing AI systems are nearly blinded to them. In this talk, I will walk through our effort towards enabling 3D behavior imaging---a computational model that allows precise measurements of microscopic social signals from numerous multiview cameras. A key challenge is that social interactions inherently induce self-occlusion, which fundamentally limits accurate 3D reconstruction from the image streams. I will argue that associating semantic meaning with geometry, e.g., holistic finger pose, provides a strong cue to predict the missing data. To learn such visual semantics, I will introduce a new large-scale human behavior dataset called HUMBI scanned by 107 HD cameras at Minnesota State Fair. In the second part of the talk, I will discuss a computational approach to measure free-ranging behaviors of monkeys for neuroscience study. Unlike humans, these monkeys are challenging due to lack of annotation data. To address this, I will introduce a semi-supervised learning framework that leverages multiview geometry and tracking to reconstruct their motion in 3D.

Biography

Hyun Soo Park is an Assistant Professor at the Department of Computer Science & Engineering, the University of Minnesota (UMN). He is interested in computer vision approaches for behavioral imaging. He has received NSF's CRII, NSF's CAREER Awards, and CVPR 2021 Best Paper Honorable Mention Award. Prior to UMN, he was a Postdoctoral Fellow in GRASP Lab at University of Pennsylvania. He earned his Ph.D. from Carnegie Mellon University.

The Minnesota Natural Language Processing (NLP) Seminar is a venue for faculty, postdocs, students, and anyone else interested in theoretical, computational, and human-centric aspects of natural language processing to exchange ideas and foster collaboration.& The talks are every other Friday from 12 p.m. - 1 p.m. during the Fall 2021 semester.

This week's speaker, Mina Lee (Stanford University), will be giving a talk titled "Writing with Language Models."

Abstract

How has the way that we write text messages or emails changed over time with autocomplete or smart reply functionalities? This talk will cover topics centered around building writing assistant systems with language models (LMs) as well as understanding collaborative writing processes between humans and LMs, with the goal of provoking discussions on existing and future forms of interactions. Concretely, I will first focus on building and evaluating productivity tools for writing, including autocomplete and thesaurus systems. Then, I will transition to a more fundamental question of “how can we reason about interaction between humans and LMs?” and introduce our recent work on using a human-LM collaborative writing dataset to understand the capabilities and limitations of LMs.

Biography

Mina Lee is a fifth-year Ph.D. student at Stanford University advised by Percy Liang. Her research interest is to enhance human productivity and creativity in the writing process by understanding human-computer interaction and leveraging natural language processing techniques.

On October 1, applications open for the computer science and data science majors. The application deadline is December 30.

Students typically apply to a major while enrolled in fall semester courses during their sophomore year (third semester).

Submit your application at the appropriate link below:

• CSE student application (Computer Science B.S. & Data Science B.S. programs)
• CLA student application (Computer Science B.A. programs)

All applicants will be notified of their admission decision via email within three weeks of the application deadline.