Search result: Catalogue data in Autumn Semester 2021

Number	Title	Type	ECTS	Hours	Lecturers
Data Science Master
Seminar
252-5051-00L	Advanced Topics in Machine Learning Number of participants limited to 40. The deadline for deregistering expires at the end of the fourth week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.	W	2 credits	2S	J. M. Buhmann, R. Cotterell, J. Vogt, F. Yang
Abstract	In this seminar, recent papers of the pattern recognition and machine learning literature are presented and discussed. Possible topics cover statistical models in computer vision, graphical models and machine learning.
Learning objective	The seminar "Advanced Topics in Machine Learning" familiarizes students with recent developments in pattern recognition and machine learning. Original articles have to be presented and critically reviewed. The students will learn how to structure a scientific presentation in English which covers the key ideas of a scientific paper. An important goal of the seminar presentation is to summarize the essential ideas of the paper in sufficient depth while omitting details which are not essential for the understanding of the work. The presentation style will play an important role and should reach the level of professional scientific presentations.
Content	The seminar will cover a number of recent papers which have emerged as important contributions to the pattern recognition and machine learning literature. The topics will vary from year to year but they are centered on methodological issues in machine learning like new learning algorithms, ensemble methods or new statistical models for machine learning applications. Frequently, papers are selected from computer vision or bioinformatics - two fields, which relies more and more on machine learning methodology and statistical models.
Literature	The papers will be presented in the first session of the seminar.
263-3504-00L	Hardware Acceleration for Data Processing Number of participants limited to 24. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.	W	2 credits	2S	G. Alonso
Abstract	The seminar will cover topics related to data processing using new hardware in general and hardware accelerators (GPU, FPGA, specialized processors) in particular.
Learning objective	The seminar will cover topics related to data processing using new hardware in general and hardware accelerators (GPU, FPGA, specialized processors) in particular.
Content	The general application areas are big data and machine learning. The systems covered will include systems from computer architecture, high performance computing, data appliances, and data centers.
Prerequisites / Notice	Students taking this seminar should have the necessary background in systems and low level programming.
263-5156-00L	Beyond iid Learning: Causality, Dynamics, and Interactions Number of participants limited to 60. The deadline for deregistering expires at the end of the second week of the semester. Students who are still registered after that date, but do not attend the seminar, will officially fail the seminar.	W	2 credits	2S	M. Mühlebach, A. Krause, B. Schölkopf
Abstract	Many machine learning problems go beyond supervised learning on independent data points and require an understanding of the underlying causal mechanisms, the interactions between the learning algorithms and their environment, and adaptation to temporal changes. The course highlights some of these challenges and relates them to state-of-the-art research.
Learning objective	The goal of this seminar is to gain experience with machine learning research and foster interdisciplinary thinking.
Content	The seminar will be divided into two parts. The first part summarizes the basics of statistical learning theory, game theory, causal inference, and dynamical systems in four lectures. This sets the stage for the second part, where distinguished speakers will present selected aspects in greater detail and link them to their current research. Keywords: Causal inference, adaptive decision-making, reinforcement learning, game theory, meta learning, interactions with humans.
Lecture notes	Further information will be published on the course website: https://beyond-iid-learning.xyz/
Prerequisites / Notice	BSc in computer science or related field (engineering, physics, mathematics). Passed at least one learning course, such as ``Introduction to Machine Learning" or ``Probabilistic Artificial Intelligence".
401-5680-00L	Foundations of Data Science Seminar	E-	0 credits		P. L. Bühlmann, A. Bandeira, H. Bölcskei, F. Yang
Abstract	Research colloquium
Learning objective
401-3620-20L	Student Seminar in Statistics: Inference in Some Non-Standard Regression Problems Number of participants limited to 24. Mainly for students from the Mathematics Bachelor and Master Programmes who, in addition to the introductory course unit 401-2604-00L Probability and Statistics, have heard at least one core or elective course in statistics. Also offered in the Master Programmes Statistics resp. Data Science.	W	4 credits	2S	F. Balabdaoui
Abstract	Review of some non-standard regression models and the statistical properties of estimation methods in such models.
Learning objective	The main goal is the students get to discover some less known regression models which either generalize the well-known linear model (for example monotone regression) or violate some of the most fundamental assumptions (as in shuffled or unlinked regression models).
Content	Linear regression is one of the most used models for prediction and hence one of the most understood in statistical literature. However, linearity might be too simplistic to capture the actual relationship between some response and given covariates. Also, there are many real data problems where linearity is plausible but the actual pairing between the observed covariates and responses is completely lost or at partially. In this seminar, we review some of the non-classical regression models and the statistical properties of the estimation methods considered by well-known statisticians and machine learners. This will encompass: 1. Monotone regression 2. Single index model 3. Unlinked regression
Literature	In the following is the tentative material that will be read and studied by each pair of students (all the items listed below are available through the ETH electronic library or arXiv). Some of the items might change. 1. Chapter 2 from the book "Nonparametric estimation under shape constraints" by P. Groeneboom and G. Jongbloed, 2014, Cambridge University Press 2. "Nonparametric shape-restricted regression" by A. Guntuoyina and B. Sen, 2018, Statistical Science, Volume 33, 568-594 3. "Asymptotic distributions for two estimators of the single index model" by Y. Xia, 2006, Econometric Theory, Volume 22, 1112-1137 4. "Least squares estimation in the monotone single index model" by F. Balabdaoui, C. Durot and H. K. Jankowski, Journal of Bernoulli, 2019, Volume 4B, 3276-3310 5. "Least angle regression" by B. Efron, T. Hastie, I. Johnstone, and R. Tibshirani, 2004, Annals of Statsitics, Volume 32, 407-499. 6. "Sharp thresholds for high dimensional and noisy sparsity recovery using l1-constrained quadratic programming (Lasso)" by M. Wainwright, 2009, IEEE transactions in Information Theory, Volume 55, 1-19 7."Denoising linear models with permuted data" by A. Pananjady, M. Wainwright and T. A. Courtade and , 2017, IEEE International Symposium on Information Theory, 446-450. 8. "Linear regression with shuffled data: statistical and computation limits of permutation recovery" by A. Pananjady, M. Wainwright and T. A. Courtade , 2018, IEEE transactions in Information Theory, Volume 64, 3286-3300 9. "Linear regression without correspondence" by D. Hsu, K. Shi and X. Sun, 2017, NIPS 10. "A pseudo-likelihood approach to linear regression with partially shuffled data" by M. Slawski, G. Diao, E. Ben-David, 2019, arXiv. 11. "Uncoupled isotonic regression via minimum Wasserstein deconvolution" by P. Rigollet and J. Weed, 2019, Information and Inference, Volume 00, 1-27
Prerequisites / Notice	The students need to be comfortable with regression models, classical estimation methods (Least squares, Maximum Likelihood estimation...), rates of convergence, asymptotic normality, etc.

Page 1 of 1