Join us at The Garage to hear from Arjun Ravi Kannan, Director of Data Science Research at Discover, who will provide insight on the near future and the ideas pushing it forward.

Register Now

T-Stochastic Graphs

Karl Rohe, Professor of Statistics, University of Wisconsin-Madison

Abstract: Previous statistical approaches to hierarchical clustering for social network analysis all construct an "ultrametric" hierarchy. While the assumption of ultrametricity has been discussed and studied in the phylogenetics literature, it has not yet been acknowledged in the social network literature. We show that "non-ultrametric structure" in the network introduces significant instabilities in the existing top-down recovery algorithms. To address this issue, we introduce an instability diagnostic plot and use it to examine a collection of empirical networks. These networks appear to violate the "ultrametric" assumption. We propose a deceptively simple class of probabilistic models called T-Stochastic Graphs which impose no topological restrictions on the latent hierarchy. Perhaps surprisingly, this model generalizes the previous models. To illustrate this model, we propose six alternative forms of hierarchical network models and then show that all six are equivalent to the T-Stochastic Graph model. These alternative models motivate a novel approach to hierarchical clustering that combines spectral techniques with the well-known Neighbor-Joining algorithm from phylogenetic reconstruction. We prove this spectral approach is statistically consistent.

Related Info

Friday / CS Distinguished Lecture
May 10th / 12:00 PM
Hybrid / Mudd 3514

Speaker
Shafi Goldwasser; Simons Institute for the Theory of Computing, University of California Berkeley

Talk Title
Trust, Backdoor Vulnerabilities and Possible Mitigations

Abstract
Cryptographic tools and models enable to trust the use of technology platforms controlled by worst case computationally bounded adversaries. In this talk I will use cryptographic modeling and tools to view trust dilemmas in various phases of the machine learning pipelines. We will touch on privacy in the training stage, verification of properties of
machine learning models, and the possibility of achieving robustness in presence of backdoors.

Biography

Shafi Goldwasser is Director of the Simons Institute for the Theory of Computing, and Professor of Electrical Engineering and Computer Science at the University of California Berkeley. Goldwasser is also the RSA Professor (post tenure) of Electrical Engineering and Computer Science at MIT and Professor Emeritus of Computer Science and Applied Mathematics at the Weizmann Institute of Science, Israel. Goldwasser holds a B.S. Applied Mathematics from Carnegie Mellon University (1979), and M.S. and Ph.D. in Computer Science from the University of California Berkeley (1984).

Goldwasser's contributions include the introduction of probabilistic encryption, interactive zero knowledge protocols, elliptic curve primality testings, hardness of approximation proofs for combinatorial problems, combinatorial property testing, and pseudo deterministic algorithms.

Goldwasser was the recipient of the ACM Turing Award in 2012, the Gödel Prize in 1993 and in 2001, the ACM Grace Murray Hopper Award in 1996, the RSA Award in Mathematics in 1998, the ACM Athena Award for Women in Computer Science in 2008, the Benjamin Franklin Medal in 2010, the IEEE Emanuel R. Piore Award in 2011, the Simons Foundation Investigator Award in 2012, and the BBVA Foundation Frontiers of Knowledge Award in 2018. Goldwasser is a member of the NAS, NAE, AAAS, the Russian Academy of Science, the Israeli Academy of Science, the London Royal Mathematical Society and a Foreign Member of the Royal Society. Goldwasser holds honorary degrees from Ben Gurion University, Bar Ilan University, Carnegie Mellon University, Haifa University, University of Oxford, and the University of Waterloo, and has received the UC Berkeley Distinguished Alumnus Award and the Barnard College Medal of Distinction.

Research Area/Interests
Cryptography, Complexity, Probabilistic Algorithms

Zoom: https://northwestern.zoom.us/j/99797040711?pwd=OWtvMGE1TU0rNmdkUEtqb2IrNmJEUT09

Scikit-Learn is one of the major libraries for machine learning in Python. This series comprises four workshops designed to give you a map of Scikit-Learn’s different functionalities and place you on firm ground to start using it for your machine-learning projects.

Part 4 - Unsupervised Learning and Beyond
Unsupervised learning uses machine learning to analyze unlabeled datasets without human supervision. Several real-world problems require discovering hidden patterns in data. In this workshop, you will learn about different unsupervised learning methods, such as dimensionality reduction and clustering, and how to process your data to apply these algorithms. We will also discuss other machine learning methods and future steps.

Prerequisites: Basic familiarity with Python is required. Familiarity with NumPy is highly recommended. No previous machine learning or statistics experience is necessary, but it will be helpful.

Register Now

Artificial intelligence (AI) is already changing society and impacting the nature of research, raising important questions about how data is gathered, analyzed, and reported, who is considered a researcher, and the ethics behind the conduct of research. To help us unpack some of these important and timely questions, the Northwestern University Institutional Review Board Office is proud to host Christina Maimone, Northwestern Information Technology Research Computing and Data Services Associate Director, in a Brown Bag session focused on the ethical and compliant use of AI in human research.

Dr. Mainmone will address everything from technological principles to security and compliance rules to integrity and ethical considerations for using AI tools in human research. For those exploring the use of AI technologies in their work, this session will also cover potential uses of AI throughout the research process, from project development to the analysis and publication of research results. Finally, attendees will leave with resources and support available at Northwestern as well as knowledge on principles guiding the evaluation of the use of AI tools. We look forward to hosting you!

Related Info

Register Now

New Developments, Industrial Applications, and Opportunities in Generative AI

Join us for an exciting event exploring the latest advancements in Generative AI! This in-person gathering will take place at the Hyatt Centric Chicago Magnificent Mile in Chicago, IL. Discover how Generative AI is revolutionizing varied industries and uncover the endless possibilities it offers. Whether you're a tech enthusiast, researcher, or industry professional, this event is a must-attend. Network with like-minded individuals, engage in thought-provoking discussions, and gain valuable insights from expert speakers. Don't miss out on this unique opportunity to stay ahead of the curve in the world of AI!

Register Now

Open to Northwestern Medicine professionals and the broader research and patient community within Northwestern University and the Greater Chicago area, our mission is to establish a thriving healthcare AI ecosystem that fosters collaboration and supports a network of dedicated scholars and professionals. We are here to promote research, innovation, and leadership while facilitating the seamless translation of AI advancements into the realm of biomedicine.

To ensure our forum delivers the most pertinent insights into AI's application across various aspects of healthcare, we have assembled a distinguished advisory board. This board comprises esteemed faculty from the fields of medicine, engineering, art and science, as well as senior leaders of the healthcare system. The advisory board is chaired by Prof. Yuan Luo, Chief AI Officer at I.AIM and Northwestern University Clinical and Translational Sciences Institute (NUCATS).

Join us in shaping the future of healthcare through the power of artificial intelligence, as we foster a vibrant community of scholars, patients, professionals and leaders dedicated to driving innovation in this critical field.

Bi-weekly meetings take place on the Chicago campus on Fridays, 10-11am CT. This event is hybrid. In person attendees will also enjoy light refreshments and networking opportunities.

Related Info

Register Now

An Automatic Finite-Sample Robustness Check: Can Dropping a Little Data Change Conclusions?

Tamara Broderick, Associate Professor, Department of Electrical Engineering and Computer Science at MIT

Abstract: Practitioners will often analyze a data sample with the goal of applying any conclusions to a new population. For instance, if economists conclude microcredit is effective at alleviating poverty based on observed data, policymakers might decide to distribute microcredit in other locations or future years. Typically, the original data is not a perfect random sample from the population where policy is applied -- but researchers might feel comfortable generalizing anyway so long as deviations from random sampling are small, and the corresponding impact on conclusions is small as well. Conversely, researchers might worry if a very small proportion of the data sample was instrumental to the original conclusion. So we propose a method to assess the sensitivity of statistical conclusions to the removal of a very small fraction of the data set. Manually checking all small data subsets is computationally infeasible, so we propose an approximation based on the classical influence function. Our method is automatically computable for common estimators. We provide finite-sample error bounds on approximation performance and a low-cost exact lower bound on sensitivity. We find that sensitivity is driven by a signal-to-noise ratio in the inference problem, does not disappear asymptotically, and is not decided by misspecification. Empirically we find that many data analyses are robust, but the conclusions of several influential economics papers can be changed by removing (much) less than 1% of the data.

Related Info

This event will explore the role of AI in creative performance contexts. Panelists Thomas DeFrantz, Duri Long, and Ozge Samanci discuss opportunities for AI to expand creative possibilities in performance, challenges presented by live interaction with AI technology, and ethical issues surrounding the use of AI in creative performance. After short presentations and a moderated group discussion, the event will close with a live showcase of a performance project that creatively operationalizes AI.

Dr. Thomas DeFrantz, Professor, Performance Studies and Theatre, directs SLIPPAGE: Performance|Culture|Technology; the group explores emerging technology in live performance applications. He believes in our shared capacity to do better and engage creative spirit for a collective good that is anti-racist, proto-feminist, and queer affirming. He convenes the Black Performance Theory working group as well as the Collegium for African Diaspora Dance, a growing consortium of 325 researchers committed to exploring Black dance practices in writing.

Dr. Duri Long, Assistant Professor, Communications Studies, is a human-centered AI researcher interested in issues surrounding AI literacy and human-AI interaction. Dr. Long’s research looks at how humans interact and learn as a way of informing the design of public AI literacy interventions as well as the development of AI that can interact naturally and improvise creatively with people in complex social environments. She employs a variety of methodologies and theoretical frameworks in her research, drawing on the learning sciences, design research, and cognitive science. She has experience working with artists and museums around the country to develop co-creative, embodied exhibits and art installations involving AI and technology.

Dr. Ozge Samanci, Associate Professor, Radio/Television/Film, is a media and comic artist. Her areas of interest include interactive media art, installation art, virtual reality storytelling, interaction design, full-body interaction, location-based art, comics and graphic novels. Her recent interactive art installations have roots in the natural sciences and explore the tendency of human beings to perceive themselves above all ecosystems.

Sponsored by the Provost’s Generative AI Advisory Committee

Register Now

Next Steps in Python Workshop Series is a seven-part series covering intermediate Python skills, tips, and tricks guaranteed to make your coding life easier. You do not need to attend each session to participate - there is a new lesson each week.

Each one-hour session meets via Zoom on Wednesdays at noon, CDT.  

Parsing text with NLTK
NLTK is one of Python's main libraries for natural language processing (NLP). This workshop introduces the library by focusing on how to parse text to create bags of words. In other words, this workshop teaches how to go from raw text (a string) to a list of words that can be used for different NLP methods.

Prerequisites: Participants should be familiar with Python at an introductory level.

Register Now

Speaker:

Serguei Saavedra, Associate Professor, Department of Civil and Environmental Engineering, MIT

Title:

How Do Ecological Systems Become (re)Assembled?

Abstract:

One of the most iconic thought experiments in biology is what would happen if we could rewind the tape of life on Earth and play it again. Would the tape have a different story in every replay? Or is there a general order of events? The relevance of this thought experiment is not just philosophical or counterfactual, because (re)assembly processes undergone by ecological systems, from microbes to mega-fauna, are continuously replicating the experiment. By integrating theoretical and empirical work, in this talk I will provide a guideline to increase our understanding about the (re)assembly possibilities of ecological systems. Explaining and predicting the (re)assembly of ecological systems underpins our ability to develop successful interventions in bio-restoration, bio-technologies, and bio-medicine.

Speaker Bio:

Serguei Saavedra is an Associate Professor at MIT in the Department of Civil and Environmental Engineering. He is also an external faculty at Santa Fe Institute. Serguei is a theoretical ecologist focused on understanding the feasibility of observing the emergence, transformations, and regeneration of ecological systems under environmental changes. Before joining MIT in 2016, Serguei studied systems engineering in Mexico; specialized in mathematical modeling at Genoa University; completed his PhD in engineering science at Oxford University; and did his postdoctoral work at the NICO (under the mentorship of Brian Uzzi), Doñana Biological Station, and in the department of environmental systems at ETH.

Location:

In person: Chambers Hall, 600 Foster Street, Lower Level
Remote option: https://northwestern.zoom.us/j/91082510906
Passcode: NICO2024

About the Speaker Series:

Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems, data science and network science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.

Related Info

Join us at The Garage to hear from Alex Castrounis, Founder & CEO at Why of AI, who will provide insight on the near future and the ideas pushing it forward.

Castrounis is the founder and CEO of Why of AI, a book author on AI, and an adjunct professor of AI for Northwestern University's Kellogg & McCormick MBAi program. He has over two decades of experience advising startups to Fortune 100 companies on using data, analytics, and AI models to drive business growth and customer success.

Register Now

Speaker:

Joseph Paulsen, Associate Professor, Department of Physics, Syracuse University

Title:

TBA

Abstract:

TBA

Speaker Bio:

Joseph Paulsen earned a bachelor's degrees in Mathematics and Physics from St. Olaf College in Northfield, MN, and he completed his PhD in Physics at the University of Chicago with Sidney Nagel. He won a National Science Foundation CAREER Award for his work that studies connections between geometry and mechanics in thin materials. Outside of science, one of his passions is trying to squirrel away as much time as possible to ski with his 7-year-old daughter (his son and his wife are not skiers... yet).

Location:

In person: Chambers Hall, 600 Foster Street, Lower Level
Remote option: https://northwestern.zoom.us/j/94291553667
Passcode: NICO2024

About the Speaker Series:

Wednesdays@NICO is a vibrant weekly seminar series focusing broadly on the topics of complex systems, data science and network science. It brings together attendees ranging from graduate students to senior faculty who span all of the schools across Northwestern, from applied math to sociology to biology and every discipline in-between. Please visit: https://bit.ly/WedatNICO for information on future speakers.

Related Info