Graduate students from UIC, NU, TTIC, UC, and IIT may request to take these courses and receive credit at their home institutions (or to simply audit these courses). Note that credits received for taking these courses might not correspond exactly with the listed course and will be determined in consultation with the IDEAL site director1 of the graduate student’s home institution. Each course will run according to the schedule of the respective university offering the course. You may request to register for courses outside your home institution by filling out this form.

[To facilitate receiving credit at your home institution, please fill the following form.]

University of Illinois at Chicago (UIC):

MCS 501                                              Computer Algorithms II (in-person) 

Lev Reyzin                                            Addams Hall 307 

MWF 9:00–9:50 am 

This course will introduce students to the fundamental ideas underlying modern algorithmic  techniques. Students will be taught how to design and analyze approximation algorithms and  randomized algorithms, as well as other advanced topics. 

ECE 594                                                  Coding Theory (in-person)  

Natasha Devroye                                  Burnham Hall 304 

TR 12:30–1:45 pm 

Graduate-level introduction to coding theory. A mix/balance of theory and programming practice.  Topics include both a few algebraic codes (BCH, RS, RM), convolutional codes, trellis-moded  modulation, as well as more modern itertive codes (Turbo, LDPC) and the latest polar codes.  Forays into research applications by folks at UIC including coding for distributed storage and deep-learned error correcting codes.. 

ECE 491                                                  Introduction to Neural Networks (hybrid) 

Ahmet Enis Cetin                                  Online / Thomas Beckham Hall 180G 

TR 12:30–1:45 pm 

An introductory course to neural networks. 

ECE 491                                                Information and Learning (in-person) 

Mesrob Ohannessian                        Lecture Center A2 

TR 9:30–10:45 am 

A first mathematical look at what information is, what it means to learn, and how the two are  related. This course covers the basics of statistical inference and learning under the lens of  information theory.  This means that in addition to specific methods and algorithms that acquire  knowledge from observations, this course also highlights the limits of what is possible and explains  what it would take to reach them. Concepts are illustrated with applications. Topics covered:  Statistical Inference, Entropy and Compression, Concentration Inequalities, Efficiency and  Universality, PAC Learning, Model Complexity, Regularization, Mutual Information and Lower  Bounds.

 

Northwestern University (NU):

ELEC_ENG 428                                  Information Theory and Learning (in-person)

Dongning Guo                                  Swift Hall 107 

[Winter] MW 2:00–3:20 pm 

COMP_SCI 496                                   Foundations of Quantum Computing (in-person)

Aravindan Vijayaraghavan               Tech LR 5 

[Winter] TR 9:30–10:50 am 

STAT 430-2                                        Probability for Statistical Inference 2 (in-person)

Miklos Racz                                       Annenberg Hall G29 

[Winter] TR 11:00 am–12:20 pm 

(description pending) 

(Spring courses TBD)

Toyota Technological Institute at Chicago (TTIC):

TTIC 31020                                       Intro to Machine Learning (in-person) 

Nati Srebro                                       TTIC 530 

[Winter] TR 1:30–2:50 pm (Lectures) F 1:30–2:30 pm (Tutorial) 

PhD level conceptual and practical introduction to modern machine learning. 

TTIC 31010                                      Algorithms (in-person) 

CMSC 37000-1 

Yury Makarychev                            TTIC 530 

[Winter] TR 1:30–2:50 pm (Lectures) F 1:30–2:30 pm (Tutorial) 

PhD level course on Algorithms.

TTIC 31260                                    Algorithmic Game Theory (in-person)
Avrim Blum                                    TTIC 530
[Spring] MW 1:30–2:50 pm

A PhD-level course on Algorithmic Game Theory. Topics include: solution concepts in game theory, such as Nash equilibrium and correlated equilibrium, and connections to learning theory; the price of anarchy in routing and congestion games; computational social choice: the axiomatic approach to ranking systems and crowdsourcing, manipulation; algorithmic mechanism design, focusing on truthful approximation algorithms; market design, with an emphasis on optimization and incentives; diffusion of technologies and influence maximization in social networks; and procedures for fair division, such as cake cutting algorithms.

TTIC 31180                                       Probabilistic Graphical Models (in-person)
Matt Walter                                       TTIC 530
[Spring] TR 9:30am–10:50am

“Many problems in machine learning, computer vision, natural language processing, robotics, computational biology, and beyond require modeling complex interactions between large, heterogeneous collections of random variables. Graphical models combine probability theory and graph theory to provide a unifying framework for representing these relationships in a compact, structured form. Probabilistic graphical models decompose multivariate joint distributions into a set of local relationships among small subsets of random variables via a graph. These local interactions result in conditional independencies that afford efficient learning and inference algorithms. Moreover, their modular structure provides an intuitive language for expressing domain-specific knowledge, and facilitates the transfer of modeling advances to new applications. This graduate-level course will provide a strong foundation for learning and inference with probabilistic graphical models. The course will first introduce the underlying representational power of graphical models, including Bayesian and Markov networks, and dynamic Bayesian networks. Next, the course will investigate contemporary approaches to statistical inference, both exact and approximate. The course will then survey state-of-the-art methods for learning the structure and parameters of graphical models.”

 

Illinois Institute of Technology (IIT):

CS 595                                          Trustworthy Machine Learning (hybrid) 

Binghui Wang                              Stuart Building 113 

MW 10:00-11:15am 

Machine learning (ML), or Artificial intelligence (AI) in general, has achieved many breakthroughs  in both academia and industry and changed our everyday life as well. On the other hand, recent  studies show that ML/AI techniques can cause serious security/privacy threats when in the hand of  an attacker, and ML/AI itself is also vulnerable to adversarial security/privacy attacks. Thus,  understanding ML/AI In adversarial settings is extremely important and necessary at present. In this  course, we will mainly follow two directions: 1) Security and privacy for ML/AI; 2) ML/AI for security  and privacy. In 1), we will study the security/privacy vulnerabilities of an ML/AI system itself, as well  as mitigating these vulnerabilities. In 2), we will study how an attacker can leverage ML/AI to  perform security/privacy threats, as well as designing methods to alleviate these threats. 

MATH 569                                 Statistical Learning (in-person) 

Ming Zhong                             Perlstein Hall 108 

TR 10:00-11:15am

University of Chicago (UC):

CMSC 35401                             The Interplay of Learning and Game Theory (in-person)

Haifeng Xu                                  Ryerson Physical Laboratory 255 

[Winter] R 2:00–4:50 pm (15 min break in the middle) 

This is a graduate level course covering topics at the interface between machine learning and  game theory. In many economic or game-theoretic applications, the problem either lacks sufficient  data or is too complex. In such cases, machine learning theory helps to design more realistic or  practical algorithms. Conversely, in many application of machine learning or prediction, the  algorithms have to obtain data from self-interested agents whose objectives are not aligned with  the algorithm designer. In those settings, the algorithms have to take into account these agents’  strategic behaviors. These problems form an intriguing interplay between machine learning and  game theory, and have attracted a lot of recent research attention. This course will discuss several recent research directions in this space. Our goal is to cover (some selected) basic results in the  following four directions. Alone the way, we will also cover necessary basics to game theory, learning theory, mechanism design, prediction and information aggregation. 

STAT 37786                               Topics in Mathematical Data Science: 

Cong Ma                                     Spectral Methods and Nonconvex Optimization (in-person)

                                                      Jones Laboratory 226 

[Winter] TR 9:30–10:50 am 

Traditional supervised learning assumes that the training and testing distributions are the same.  Such a no-distribution-shift assumption, however, is frequently violated in practice. In this course,  we survey topics in machine learning in which distribution shifts naturally arise. Possible topics  include supervised learning with covariate shift, off-policy evaluation in reinforcement learning, and  offline reinforcement learning.

STAT 28000                             Optimization (in-person) 

Lek-Heng Lim                         (location TBD) 

[Spring] (time TBD) 

Undergraduate course on optimization.

Join Our Newsletter