Past Events

Advisory: Application deadline is March 21, 2022

Summer Math Boot Camp Vll poster

Organizers:

• Thomas Hoft, University of St. Thomas
• Daniel Spirn, University of Minnesota, Twin Cities

The Math-to-Industry Boot Camp is an intense six-week session designed to provide graduate students with training and experience that is valuable for employment outside of academia. The program is targeted at Ph.D. students in pure and applied mathematics. The boot camp consists of courses in the basics of programming, data analysis, and mathematical modeling. Students work in teams on projects and are provided with training in resume and interview preparation as well as teamwork.

There are two group projects during the session: a small-scale project designed to introduce the concept of solving open-ended problems and working in teams, and a "capstone project" that is posed by industrial scientists. Recent industrial sponsors included Gargill, Securian Financial and CH Robinson. 

Weekly seminars by speakers from many industry sectors provide the students with opportunities to learn about a variety of possible future careers.

Eligibility

Applicants must be current graduate students in a Ph.D. program at a U.S. institution during the period of the boot camp.

Logistics

The program will take place online. Students will receive a $2,000 stipend.

Applications

To apply, please supply the following materials through the link at the top of the page:

• Statement of reason for participation, career goals, and relevant experience
• Unofficial transcript, evidence of good standing, and have full-time status
• Letter of support from advisor, director of graduate studies, or department chair

Selection criteria will be based on background and statement of interest, as well as geographic and institutional diversity. Women and minorities are especially encouraged to apply. Selected participants will be contacted in April.

Projects and teams

CH Robinson: Team 1 — Dynamic pricing in logistics

• Mentor Brady Thompson, CH Robinson
• Mentor Veronika Koubova, CH Robinson
• Mentor Matthew Smith, CH Robinson
• Mentor Orion Wynblatt, CH Robinson
• Mentor Daniel Prentice, CH Robinson
• Ibrahem Aljabea, Louisiana State University
• Abhinav Chand, Kansas State University
• Mengting Chao, University of Maryland
• Zhaobidan (Amy) Feng, Texas A & M University
• Vanny Khon, Boston University
• Christian McRoberts, Iowa State University

Pricing in logistics is a very fast paced environment. Pricing managers need to be aware of the constant changes in the market, and be able to adapt quickly. Depending on the business needs, whether that be to increase profit or increase volume, we need to be able to quickly explore the data, develop a model, and test to determine if the strategy is meeting the business goals. Our team of data scientists work in Less-Than-Truckload pricing, a fast growing market segment driven by recent trends in the supply chain. Given a business goal, we use historical data to build a pricing strategy that we believe will achieve the goal, and then run controlled experiments to determine the success of our strategy.

A boot camp student working on our project would become familiarized with dynamic pricing, as well as research surrounding multi-choice pricing dynamics. They will develop the python skills needed to implement machine learning models that use historical and streaming data, including reinforcement learning. Lastly, it is expected that they would be able to manage an online controlled experiment to test the quality of their pricing strategy.

ITM TwentyFirst: Team 2 — Identifying Longevity Risk with Machine Learning

• Mentor Jonathan Hill, ITM TwentyFirst LLC
• Mentor Tianze Li, ITM TwentyFirst LLC
• Shan Chen, University of Minnesota, Twin Cities
• Haridas Kumar Das, Oklahoma State University
• Kimberlyn Eversman, University of Tennessee
• Dumindu Sandakith Kasiwatte Kankanamge, Vanderbilt University
• Mark Roach, Michigan State University
• Matthew Wynne, University of Washington

Traditional approaches to predicting life outcomes are robust and interpretable but come with limitations. They are limited in the number of interactions between medical conditions (“comorbidities”) that can be considered, unable to handle missing values, and have a fixed base table shape. We developed a machine learning model (the Longevity Risk Model) to address these limitations. Its target is to identify insureds where our traditional model (“RevH”) is likely too long (low longevity risk) or too short (high longevity risk). Our goal is to expand the ideas behind the Longevity Risk Model and find creative ways to improve its predictions. These improvements might include, but are not limited to, identifying COVID deaths in our dataset and adding COVID as a feature to the model, using quantile objective functions to make prediction intervals, altering the structure of the stacked models, and predicting the conditional probability of outliving life expectancy.

We will use Python 3, along with a unique world-class dataset on senior life outcomes provided by ITM TwentyFirst, a Minneapolis-based life settlements servicing company.

US Bank: Team 3 — Forecasting Prepayments in High Interest Rate Environment

• Mentor Chistopher Jones, US Bank
• Caroline Bang, Iowa State University
• Katheryn Beck, University of Kansas
• Zanbing Dai, University of Minnesota, Twin Cities
• Leonardo Digiosia, Rice University
• Arpan Pal, Texas A & M University
• Bo Zhu, University of Minnesota, Twin Cities

U.S. agency 1 residential mortgage-backed securities (MBS) are the largest and most liquid securitized asset class in the world. Banks, insurance companies, and money managers invest in MBS because they provide an attractive yield relative to U.S. Treasury securities with comparable credit risk. However, unlike most fixed income securities, which have specified contractual coupon and principal payments, the timing and amount of MBS cash flows is uncertain. This is because MBS are pools of individual mortgages on which the borrower has the right to prepay the loan at any given time during the life of the loan. Prepayment risk, which impacts the yield and interest rate risk of an MBS comes from five sources:

Rate/term refinance which occur when borrowers lower interest payments or shorten the term of the current mortgage.

Cash-out refinance which involve extracting equity from a home.

Involuntary buyouts, which in the case of agency MBS result in an early return of principal. However, the timing is contingent on the GSEs or GNMA loan servicers.

Curtailments, which are partial prepayment or full payoff before maturity.

Turnover, which is caused by geographic migration and home upgrades. Turnover creates a baseline level of prepayments that are highly seasonal.

The COVID-19 crisis and response by the Federal Reserve resulted in a low-rate environment that elevated both levels of refinance and buyout activity. Since the initiation of quantitative tightening, sustained inflation, and rising interest rates, refinance activity has slowed considerably. At present, a major question affecting the risk profile of MBS is to what extent prepayment activity will decrease. With diminishing refinance incentives, the major sources of prepayment are now turnover, curtailment, and buyouts. As a baseline level of prepayment activity, understanding turnover is important to evaluating the risks of mortgage-backed securities. The goal of this project is to use loan-level mortgage data and macroeconomic data to quantify turnover prepayment speed.

Advisory: 

• Please see below for detailed application instructions.
• The deadline for application is February 28, 2022.

Organizers

• Christine Berkesch — University of Minnesota, Twin Cities
• Michelle Manes — University of Hawaii
• Priyam Patel — The University of Utah
• Candice Price — Smith College
• Adriana Salerno — Bates College
• Bianca Viray — University of Washington

Apply

To apply, please submit the following documents:

1. Personal Statement.

Please write a brief (max 5,000 character) statement describing your interest in attending the Roots of Unity workshop. We are interested in understanding how your identities have impacted your mathematical journey, as well as your areas of interest and approximate timeline for choosing an advisor. To the extent that you feel comfortable sharing, please describe your journey, possibly including: your experiences collaborating with, supporting, and being supported by your peers, particularly those from groups marginalized in mathematics, and any obstacles that you have faced. On two separate additional pages in this document (that is not part of the max character count), please provide: (i) a list of the graduate courses you have taken in topics related to the workshop, and (ii) your ranking of topic preferences for the working groups (arithmetic geometry, combinatorics, commutative algebra, geometry, topology).  

2. Resume or CV

3. One letter of reference

One letter of reference from someone who can speak to your potential in your graduate program. Your letter-writer will be emailed instructions on how to upload their letter to MathPrograms. Please email your letter-writer the following sentences: 

I am asking you to provide a brief letter of reference to support my application to the Roots of Unity workshop. This week-long workshop is designed to support women, particularly women of color, who have completed 1–3 years of graduate school and are considering research in algebra, combinatorics, geometry, topology, or number theory. The program would appreciate your candid opinion of me as a student, including in what capacity you have worked with me, my potential for success in my graduate program in the mathematical sciences, how the Roots of Unity workshop might benefit me, and how I will benefit the Roots of Unity workshop. For more information about the workshop, please see the Roots of Unity website. 

Workshop description

This week-long workshop is designed to support women, particularly women of color, who are in years 1–3 of graduate school and are considering research in algebra, combinatorics, geometry, topology, or number theory.

In a forest, underground mycorrhizal networks connect different tree species through their root systems, allowing for transfer of nutrients (van der Heijden, 2016). These networks also allow trees to communicate about dangers like pests and disease, and they are believed to enhance plant fitness and forest stability. For graduate students, too, a strong network can be critical for success, and such networks are even more important for students from groups that have been historically marginalized. We have designed the Roots of Unity workshop to assist in cultivating strong relationships among the participants, a network — seeded at the workshop and continuing throughout their careers — that will allow students to strengthen and nurture each other.

The transition to independent learning and research is a crucial and often jarring point in every graduate student's career. This transition is even more difficult for students from marginalized groups, who often have smaller support systems and may face an actively unsupportive environment at their institution. The goal of this workshop is to support, mentor, and guide students at this crucial stage in their career. 

During the workshop, mentors will guide the student participants through the (often very daunting!) experience of trying to read a paper without being an expert in the area. The participants will be broken into small working groups, each focused on a recent paper in their area of interest. Each group will be assisted throughout the week by mentors, both early career mathematicians (late stage graduate students or postdocs) and faculty members. 

The professional development component of the Roots of Unity Workshop will focus on practical tools for navigating a research career, while building community and increasing access to professionals or near-peers. These will include in-person panels and activities during the workshop and follow-up (virtual) activities throughout the year to continue nurturing the community and connections.

The program is tailored to support women of color, and our strategies reflect this priority. However, if you are a graduate student in your first three years of study and believe that this workshop will benefit you, please apply. We especially encourage applications from students who are women, nonbinary, and/or gender fluid. 

Applications received by February 28, 2022, will receive full consideration. Application decisions will be sent out no later than March 31, 2022.

Workshop groups

Commutative Algebra
Mentors: Christine Berkesch, Haydee Lindo, Patricia Klein

Combinatorics 
Mentors: Pamela Harris, Mariel Supina, Isabelle Shankar

Low Dimensional Topology and Geometry 
Mentors: Candice Price, Emille Davie, Sherilyn Tamagawa

Geometry 
Mentors: Autumn Kent, Marissa Loving, Michelle Chu

Arithmetic Geometry 
Mentors: Adriana Salerno, Lori Watson, Allechar Serrano Lopez 

Organizers

• Jim Fowler — The Ohio State University
• Kris Hollingsworth — University of Minnesota, Twin Cities
• Duane Nykamp — University of Minnesota, Twin Cities
• Matt Thomas — Cornell University

In this four-day workshop, participants will learn how to create and implement online learning experiments using the Distributed Open Education Network (Doenet, doenet.org). Doenet is designed to help faculty critically evaluate how different content choices influence student learning in their classrooms. Doenet enables instructors to quickly test hypotheses regarding the relative effectiveness of alternative approaches by providing tools to assign different variations of an activity and analyze the resulting data.

Following brief introductions and demos of features of the Doenet platform, participants will work in small groups to develop learning experiments that can be used in the college classroom, assisted by the developers of Doenet. The expectation is that participants will leave the workshop with a learning experiment that they can use in their classroom the following year.

The workshop will run from 9 AM on Monday, May 23 though noon on Thursday, May 26. All organized activities will occur between 9 AM and 4 PM each day.

The workshop is open to faculty at all levels teaching STEM courses; instructors of mathematics courses are particularly encouraged to apply.

To apply, please submit the following documents through the Program Application link at the top of the page:

1. A personal statement briefly (200 words or less) stating what you hope to contribute to the discussion on learning experiments and what you hope to gain from this workshop. Include courses you teach for which you'd like to develop learning experiments. Priority will be given to those able to run learning experiments in their courses in the following year.
2. A brief CV or resume. (A list of publications is not necessary.)

This workshop is fully funded by the National Science Foundation. All accepted participants who request funding for travel and/or local expenses will receive support. There is no registration fee.

Participants who perform learning experiments on Doenet during the following academic year will be eligible to receive a small stipend to support their work.

Supported by NSF grant DUE 1915363.

Charles Smart (Yale University)

Small water droplets on patterned surfaces can form interesting shapes. I will discuss a rigorous analysis of a simple finite difference model that explains these shapes. This will include a basic introduction to free boundary problems on lattices. This is joint work with Feldman.

Myungjin Lee (Cisco)

Federated machine learning (FL) is gaining a lot of traction across research communities and industries. FL allows machine learning (ML) model training without sharing data across different parties, thus natively supporting data privacy. However, designing and executing FL jobs is not an easy task today. Flame is an open-source project that aims to ease the composition of FL jobs and the management of their lifecycle across different environments. Towards those ends, Flame is architected to be open and extensible from its inception. This talk will present an overview of the project and a demo on how the Flame system works in a Kubernetes environment.

Myungjin Lee is a Senior Researcher at Cisco's Emerging Technologies and Incubation (ET&I). He leads research on systems for edge computing. His current focus is on federated learning and its use cases at the edge. He is passionate about building software for distributed systems and computer networks.

Prior to Cisco, he worked at Salesforce as a software engineer, where he led a secure cross-datacenter communication project. He was also an Assistant Professor at the University of Edinburgh, UK, where he led research activities around systems and networks including datacenter networks, network telemetry, SDN, etc. 

Eric Weber (Iowa State University)

Abstract: The Kaczmarz algorithm is a method for solving linear systems of equations that was introduced in 1937.  The algorithm is a powerful tool with many applications in signal processing and data science that has enjoyed a resurgence of interest in recent years.  We'll discuss some of the history of the Kaczmarz algorithm as well as describe some of the recent interest and applications.  We'll then discuss how the algorithm can be used as a consensus method to process data in a distributed environment.

Dr. Eric Weber holds a Ph.D. in Mathematics from the University of Colorado.  His research interests include harmonic analysis, approximation theory and data science.  Past research includes developing novel wavelet transforms for image processing, and reproducing kernel methods for the harmonic analysis of fractals.  Current research projects include the development of new algorithms for processing distributed spatiotemporal datasets; extending alternating projection methods for optimization in non-Euclidean geometries; using harmonic analysis techniques for understanding the approximation properties of neural networks; and developing machine learning techniques to improve the diagnosis of severe wind occurrences.

Martin Molina-Fructuoso (North Carolina State University)

Registration is required to access the Zoom webinar. Martin will also be in person in 402 Walter.

Statistical depths extend the concepts of quantiles and medians to multidimensional data and can be useful to establish a ranking order within data clusters. The Tukey depth is one classical geometric construction of a highly robust statistical depth that has deep connections with convex geometry. Finding the Tukey depth for general measures is a computationally expensive problem, particularly in high dimensions.

In recent work (in collaboration with Ryan Murray) we have shown a link between the Tukey depth of measures with some degree of regularity and a partial differential equation of the Hamilton-Jacobi type. This talk will discuss a strategy based on the characteristics of the differential equation that intends to use this connection to calculate Tukey depths. This approach is inspired by other recent work which attempts to compute solutions to eikonal equations in high dimensions using characteristic-based methods for special classes of initial data.

Martin Molina-Fructuoso graduated from the University of Maryland, College Park with a PhD in Applied Mathematics advised by Profs. Antoine Mellet and Pierre-Emmanuel Jabin. He then joined North Carolina State University as a Postdoctoral Research Scholar where he worked with Prof. Ryan Murray. His interests lie in PDE-based variational methods for problems related to machine learning and in optimal transportation and its applications.

Inbar Seroussi (Weizmann Institute of Science)

Modern learning algorithms such as deep neural networks operate in regimes that defy the traditional statistical learning theory. Neural networks architectures often contain more parameters than training samples. Despite their huge complexity, the generalization error achieved on real data is small. In this talk, we aim to study the generalization properties of algorithms in high dimensions. We first show that algorithms in high dimensions require a small bias for good generalization. We show that this is indeed the case for deep neural networks in the over-parametrized regime. We, then, provide lower bounds on the generalization error in various settings for any algorithm. We calculate such bounds using random matrix theory (RMT). We will review the connection between deep neural networks and RMT and existing results. These bounds are particularly useful when the analytic evaluation of standard performance bounds is not possible due to the complexity and nonlinearity of the model. The bounds can serve as a benchmark for testing performance and optimizing the design of actual learning algorithms. Joint work with Ofer Zeitouni, more information in arxiv.org/abs/2103.14723.

Inbar Seroussi is a postdoctoral fellow in the mathematics department at the Weizmann Institute of Science, hosted by Prof. Ofer Zeitouni. Previously, she completed her Ph.D. in the applied mathematics department at Tel-Aviv University under the supervision of Prof. Nir Sochen. Her research interest includes modeling of complex and random systems in high dimensions with application to modern machine learning, physics and medical imaging. She develops and uses advanced tools drawn from statistical physics, stochastic calculus, and random matrix theory.

Philippe Barbe (Paramount)

This talk discusses similarities and differences between doing data science in academic and business environment. What are the relevant main differences between these environments? Why are the problem of different complexities? What is helpful to know? It builds on my years of experience doing both. All questions are welcome.

Philippe Barbe, PhD, is Senior Vice President of Content Data Science at Paramount (formerly ViacomCBS). In this role Philippe is responsible for data science modeling to inform content exploitation decisions across Paramount businesses. His team builds predictive models that support highly critical multi-million dollar content-related decisions in collaboration with many data science and research groups across Paramount.

Philippe received a PhD in mathematics and statistics from University Pierre et Marie Curie in Paris, France (currently Sorbonne University) and degree in management and government from ENSAE. He worked for over 20 years at the CNRS, as mathematician specialized in data science and related fields. He authored or co-authored 5 books and numerous scientific papers. He has been an invited professor in many universities worldwide, including Yale and GeorgiaTech in the US. He has been working in the media and entertainment industry since 2015.

https://www.linkedin.com/in/ph-barbe/

Joao Pereira (The University of Texas at Austin)

In this talk, I focus on the multivariate method of moments for parameter estimation. First from a theoretical standpoint, we show that in problems where the noise is high, the number of observations necessary to estimate parameters is dictated by the moments of the distribution. Second from a computational standpoint, we address the curse of dimensionality: the d-th moment of an n-dimensional random variable is a tensor with nd entries. For Gaussian Mixture Models (GMMs), we develop numerical methods for implicit computations with the empirical moment tensors. This reduces the computational and storage costs, and opens the door to the competitiveness of the method of moments as compared to expectation maximization methods. Time permitting, we connect these results to symmetric CP tensor decomposition and sketch a recent algorithm which is faster than the state-of-the-art and comes with guarantees. Collaborators include Joe Kileel (UT Austin), Tamara Kolda (MathSci.ai) and Timo Klock (Deeptech).

João is a postdoc in the Oden Institute at UT Austin, working with Joe Kileel and Rachel Ward. Previously, he was a postdoc at Duke University, working with Vahid Tarokh, and obtained is Ph.D. degree in Applied Mathematics at Princeton University, advised by Amit Singer and Emmanuel Abbe. This summer, he will join IMPA, in Rio de Janeiro, Brazil, as an assistant professor. He is broadly interested in tensor decompositions, information theory and applied mathematics.