Events
Past Event
Probability Seminar | Eren Kizildag (UIUC)
Department of Mathematics: Probability Seminar
4:00 PM
//
104, Lunt Hall
Details
Title: Statistical-Computational Tradeoffs in Random Optimization Problems
Abstract: Optimization problems with random objective functions are central in computer science, probability, and modern data science. Despite their ubiquity, finding efficient algorithms for solving these problems remains a major challenge. Interestingly, many random optimization problems share a common feature, dubbed as a statistical-computational gap: while the optimal value can be pinpointed non-constructively (through, e.g., probabilistic/information-theoretic tools), all known polynomial-time algorithms find strictly sub-optimal solutions. That is, an optimal solution can only be found through brute force search which is computationally expensive.
In this talk, I will discuss an emerging theoretical framework for understanding the fundamental computational limits of random optimization problems, based on the Overlap Gap Property (OGP). This is an intricate geometrical property that achieves sharp algorithmic lower bounds against the best known polynomial-time algorithms for a wide range of random optimization problems. I will focus on two models to demonstrate the power of the OGP framework: (a) the symmetric binary perceptron, a random constraint satisfaction problem and a simple neural network classifying/storing random patterns, widely studied in computer science, probability, and statistics communities, and (b) the random number partitioning problem as well as its planted counterpart, a classical worst-case NP-hard problem whose average-case variant is closely related to the design of randomized controlled trials. In addition to yielding sharp algorithmic lower bounds, our techniques also give rise to new toolkits for the study of statistical-computational tradeoffs in other models, including the online setting.
Time
Tuesday, November 5, 2024 at 4:00 PM - 5:00 PM
Location
104, Lunt Hall Map
Contact
Calendar
Department of Mathematics: Probability Seminar
Fall classes end
University Academic Calendar
All Day
Details
Fall classes end
Time
Saturday, December 7, 2024
Contact
Calendar
University Academic Calendar
Course Design Institute: Generative AI Edition
Searle Center Events
9:00 AM
Details
December 12 & 13
Interested in (re)designing a course to integrate more inclusive and engaging practices? Want to jumpstart building your course for winter or spring quarter?
Whether you’re enthusiastic, skeptical, or curious about using generative AI tools as course building partners, we invite you to join colleagues, Searle Center educational developers, and Northwestern IT Teaching and Learning Technologies learning engineers this December for the Course Design Institute: Generative AI Edition!
Participants will experiment with using generative AI tools to craft meaningful learning outcomes, create authentic assessments aligned to those outcomes, sequence activities accordingly, and finally, construct Canvas-ready modules.
Just like the annual Summer Course Design Institute, the Generative AI Edition will guide instructors step-by-step in developing a course where they can have confidence that all enrolled students will have the opportunity to achieve the learning outcomes—no matter how rigorous or ambitious.
Time
Thursday, December 12, 2024 at 9:00 AM - 12:00 PM
Contact
Calendar
Searle Center Events
MLDS Online Information Session
Master of Science in Machine Learning and Data Science (MLDS)
10:00 AM
Details
QUALIFY FOR INNOVATIVE AND TECHNICAL JOBS AT TOP COMPANIES
With more companies using data, the demand for data scientists continues to soar. Register for our Master of Science in Machine Learning and Data Science online information session to learn how you can take the next step in your career as an effective, knowledgeable leader in a rapidly growing field.
Learn more or register.
Time
Thursday, December 12, 2024 at 10:00 AM - 11:00 AM
Calendar
Master of Science in Machine Learning and Data Science (MLDS)
Northwestern Engineering PhD Hooding and Master's Recognition Ceremony
McCormick School of Engineering and Applied Science
4:00 PM
//
Pick-Staiger Concert Hall
Details
The ceremony will take place on Saturday, December 14 in Pick-Staiger Concert Hall, 50 Arts Circle Drive.
*No tickets required
Time
Saturday, December 14, 2024 at 4:00 PM - 6:00 PM
Location
Pick-Staiger Concert Hall Map
Contact
Calendar
McCormick School of Engineering and Applied Science
Bootcamp: Python Fundamentals (Virtual)
Northwestern IT Research Computing and Data Services
9:00 AM
Details
This four-day bootcamp provides an engaging, comprehensive, hands-on introduction to the Python programming language. Python is an extremely popular, general-purpose, versatile coding language with a shallow learning curve, meaning you can do a lot with the tools you’ll learn in this four-day workshop.
If you're already proficient in another coding language and you're looking for a beginner's introduction to Python because you want to be able to read and run Python code written by others or utilize Python packages for machine learning, web scraping, or text analysis, you should attend at least the first two-and-a-half or three days of the bootcamp. If you're looking to become a proficient Python coder, you should attend all four days of the bootcamp. The instructor will not be able to help you catch up if you miss materials.
Prerequisites: You will need to bring a laptop to participate.
Register once for all four-days.
Time
Monday, December 16, 2024 at 9:00 AM - 4:00 PM
Contact
Calendar
Northwestern IT Research Computing and Data Services
Bootcamp: Python Fundamentals (Virtual)
Northwestern IT Research Computing and Data Services
9:00 AM
Details
This four-day bootcamp provides an engaging, comprehensive, hands-on introduction to the Python programming language. Python is an extremely popular, general-purpose, versatile coding language with a shallow learning curve, meaning you can do a lot with the tools you’ll learn in this four-day workshop.
If you're already proficient in another coding language and you're looking for a beginner's introduction to Python because you want to be able to read and run Python code written by others or utilize Python packages for machine learning, web scraping, or text analysis, you should attend at least the first two-and-a-half or three days of the bootcamp. If you're looking to become a proficient Python coder, you should attend all four days of the bootcamp. The instructor will not be able to help you catch up if you miss materials.
Prerequisites: You will need to bring a laptop to participate.
Register once for all four-days.
Time
Tuesday, December 17, 2024 at 9:00 AM - 4:00 PM
Contact
Calendar
Northwestern IT Research Computing and Data Services
Bootcamp: Python Fundamentals (Virtual)
Northwestern IT Research Computing and Data Services
9:00 AM
Details
This four-day bootcamp provides an engaging, comprehensive, hands-on introduction to the Python programming language. Python is an extremely popular, general-purpose, versatile coding language with a shallow learning curve, meaning you can do a lot with the tools you’ll learn in this four-day workshop.
If you're already proficient in another coding language and you're looking for a beginner's introduction to Python because you want to be able to read and run Python code written by others or utilize Python packages for machine learning, web scraping, or text analysis, you should attend at least the first two-and-a-half or three days of the bootcamp. If you're looking to become a proficient Python coder, you should attend all four days of the bootcamp. The instructor will not be able to help you catch up if you miss materials.
Prerequisites: You will need to bring a laptop to participate.
Register once for all four-days.
Time
Wednesday, December 18, 2024 at 9:00 AM - 4:00 PM
Contact
Calendar
Northwestern IT Research Computing and Data Services
Bootcamp: Python Fundamentals (Virtual)
Northwestern IT Research Computing and Data Services
9:00 AM
Details
This four-day bootcamp provides an engaging, comprehensive, hands-on introduction to the Python programming language. Python is an extremely popular, general-purpose, versatile coding language with a shallow learning curve, meaning you can do a lot with the tools you’ll learn in this four-day workshop.
If you're already proficient in another coding language and you're looking for a beginner's introduction to Python because you want to be able to read and run Python code written by others or utilize Python packages for machine learning, web scraping, or text analysis, you should attend at least the first two-and-a-half or three days of the bootcamp. If you're looking to become a proficient Python coder, you should attend all four days of the bootcamp. The instructor will not be able to help you catch up if you miss materials.
Prerequisites: You will need to bring a laptop to participate.
Register once for all four-days.
Time
Thursday, December 19, 2024 at 9:00 AM - 4:00 PM
Contact
Calendar
Northwestern IT Research Computing and Data Services
Biological Systems that Learn
NSF-Simons National Institute for Theory and Mathematics in Biology
9:00 AM
Details
Many biological systems have evolved to embody solutions to complex inverse problems to produce desired outputs or functions; others have evolved strategies to learn solutions to complex inverse problems on much shorter (e.g. physiological or developmental) time scales. Another class of systems that solves complex inverse problems for desired outputs is artificial neural networks. A critical distinction between the biological systems and neural networks is that the former are not associated with processors that carry out algorithms such as gradient descent to solve the inverse problems. They must solve them using local rules that only approximate gradient descent. Thus a key challenge is to understand how biological systems encode local rules for experience-dependent modification in physical hardware to implement robust solutions to complex
inverse problems. A similar challenge is faced by a growing community of researchers interested in developing physical systems that can solve inverse problems on their own. Despite the differences between physical/biological systems that solve inverse problems via local rules on one hand, and neural networks that solve them using global algorithms like gradient descent on the other hand, each has the potential to inform the other. For example, the insight that overparameterization is important for obtaining good solutions generalizes from neural networks to physical/biological learning systems.
Examples of biological systems that learn at different scales include (1) biological filament networks such as the actin cortex, collagen extracellular matrix and fibrin blood clots, which maintain rigidity homeostasis as an output under constantly varying and often extreme stresses as inputs. (2) Epithelial tissues during various stages of development, which can undergo large shape changes and controlled cellular flows as desired outputs. (3) Immune systems, which constantly adapt to bind to invading pathogens as desired outputs. (4) Ecological systems, in which species can change their interactions (eg. learn to consume new species) in order to bolster their population as an output.
The goal of this workshop is to discover new core principles and mathematical tools/approaches shared across physical learning systems, biological learning systems and neural networks that will inform deeper understanding and future discovery in all 3 fields. To this end, we will bring together researchers interested in viewing biological problems through the lens of inverse problems, researchers working on physical learning, and researchers studying neural networks for a week of intensive discussion and cross-fertilization.
We envision a unique format for this workshop, focused on framing and discussing open questions rather than on recitations of recent results. We will ask a subset of participants to present pedagogical overviews of key topics to help members of disparate communities establish common intellectual ground for discussion.
Time
Monday, January 6, 2025 at 9:00 AM - 5:00 PM
Contact
Calendar
NSF-Simons National Institute for Theory and Mathematics in Biology
Biological Systems that Learn
NSF-Simons National Institute for Theory and Mathematics in Biology
9:00 AM
Details
Many biological systems have evolved to embody solutions to complex inverse problems to produce desired outputs or functions; others have evolved strategies to learn solutions to complex inverse problems on much shorter (e.g. physiological or developmental) time scales. Another class of systems that solves complex inverse problems for desired outputs is artificial neural networks. A critical distinction between the biological systems and neural networks is that the former are not associated with processors that carry out algorithms such as gradient descent to solve the inverse problems. They must solve them using local rules that only approximate gradient descent. Thus a key challenge is to understand how biological systems encode local rules for experience-dependent modification in physical hardware to implement robust solutions to complex
inverse problems. A similar challenge is faced by a growing community of researchers interested in developing physical systems that can solve inverse problems on their own. Despite the differences between physical/biological systems that solve inverse problems via local rules on one hand, and neural networks that solve them using global algorithms like gradient descent on the other hand, each has the potential to inform the other. For example, the insight that overparameterization is important for obtaining good solutions generalizes from neural networks to physical/biological learning systems.
Examples of biological systems that learn at different scales include (1) biological filament networks such as the actin cortex, collagen extracellular matrix and fibrin blood clots, which maintain rigidity homeostasis as an output under constantly varying and often extreme stresses as inputs. (2) Epithelial tissues during various stages of development, which can undergo large shape changes and controlled cellular flows as desired outputs. (3) Immune systems, which constantly adapt to bind to invading pathogens as desired outputs. (4) Ecological systems, in which species can change their interactions (eg. learn to consume new species) in order to bolster their population as an output.
The goal of this workshop is to discover new core principles and mathematical tools/approaches shared across physical learning systems, biological learning systems and neural networks that will inform deeper understanding and future discovery in all 3 fields. To this end, we will bring together researchers interested in viewing biological problems through the lens of inverse problems, researchers working on physical learning, and researchers studying neural networks for a week of intensive discussion and cross-fertilization.
We envision a unique format for this workshop, focused on framing and discussing open questions rather than on recitations of recent results. We will ask a subset of participants to present pedagogical overviews of key topics to help members of disparate communities establish common intellectual ground for discussion.
Time
Tuesday, January 7, 2025 at 9:00 AM - 5:00 PM
Contact
Calendar
NSF-Simons National Institute for Theory and Mathematics in Biology