*Based on a previous version by Michael Gutmann.*

We will have poster presentations of research papers in the second half of the course. There will be a total of 5 poster sessions. You will need to do two things (see detailed instructions below):

- Give a poster presentation on a paper (2/3 of the presentation grade)
- Write summaries for two other poster presentations: Select 2 out of 5 poster sessions and write a short summary for one presentation per each of these two poster sessions (1/3 of the presentation grade)

## Instructions

**Presentations**

The posters are designed and presented by groups of two students. Each group should
email the TA the following information by Friday 9 February:

- Names and student numbers
- 5 papers in decreasing order of preference
- Preferred date of the presentation

Please note that we cannot guarantee that we can accommodate everyone's preferences. You can use Piazza to find team-mates. If you would like to do the poster presentation alone rather than in a group, please check with the TA. Please note that individual presentations will only be possible if time slots are available.

- If the presentation is given by two students, both have to contribute equally to the poster and its presentation. Both presenters will receive the same grade.
- You should prepare a poster in A0 landscape format. You can use your favourite tool to create the poster (e.g. LaTeX, LibreOffice Impress, Adobe Illustrator, Powerpoint, ...). For LaTeX, there are templates. For example posters, have a look at the NIPS conference. Print the poster in time for the presentation.
You should
*also*send a pdf version of your poster to the lecturer on the day before your presentation. Research papers typically make a scientific contribution, which means that they propose or claim something that holds and that matters. The overall goal of the presentation is to convey the contribution made in the paper. For that purpose, the presentations should cover:

- Very briefly, what is the paper generally about?
- Background and/or brief recap of the relevant material from the lecture.
- What is proposed or claimed in the paper?
- What supporting evidence is provided?
- Why does the proposal/claim matter?

- Aim for a short (10-15 minutes) interactive presentation. Do only include as much mathematics as needed to convey the key message of the paper.
- Feel free to use diagrams and equations from the paper in your poster (with proper acknowledgement).

**Summary**

- The summary should be structured according to the five highlighted points above.
- In total, the summary of each paper should be maximally half a page. This means one to two sentences per point only. Good diagrams will be helpful.
- Please email the summary of one paper per session for a total of two sessions to the lecturer by Tuesday of the week following the presentation (at noon).

## Papers

Please feel free to propose papers yourself. Check with the lecturer about suitability.

**PCA and its extensions**

- Independent Component Analysis: Algorithms and Applications

A. Hyvarinen

Neural Networks 2000 - Robust Principal Component Analysis

E. Candes, X. Li, Y. Ma, and J. Wright

Journal of ACM 2009 - Heterogeneous Component Analysis

S. Oba, M. Kawanabe, et al

Advances in Neural Information Processing Systems 21, 2008 - Optimal Sparse Linear Encoders and Sparse PCA

M. Magdon-Ismail and C. Boutsidis

Advances in Neural Information Processing Systems 29, 2016 - On Consistency and Sparsity for Principal Components Analysis in High Dimensions

I.M. Johnstone and A.Y. Lu

Journal of the American Statistical Association 2009 - Single Pass PCA of Matrix Products

S. Wu, S. Bhojanapalli, et al

Advances in Neural Information Processing Systems 29, 2016 - Provable Non-convex Robust PCA

P. Netrapalli, U.N. Niranjan, et al

Advances in Neural Information Processing Systems 27, 2014

**Dimensionality reduction and data visualisation**

- Reducing the Dimensionality of Data with Neural Networks

G. Hinton and R. Salakhutdinov

Science 2006 - On a Connection between Kernel PCA and Metric Multidimensional Scaling

C. Williams

Advances in Neural Information Processing Systems 14, 2001 - Hubs in Space: Popular Nearest Neighbors in High-Dimensional Data

M. Radovanovic et al

Journal of Machine Learning Research 2010 - Nonlinear Dimensionality Reduction by Locally Linear Embedding (longer version)

L. Saul and S. Roweis

Science 2000 - Visualizing Data using t-SNE

L. van der Maaten and G. Hinton

Journal of Machine Learning Research 2008 - The Self-Organizing Map

T. Kohononen

Neurocomputing 1998 - Learning the Parts of Objects by Non-negative Matrix Factorization

D.D. Lee and H.S. Seung

Nature 1999 - PARAFAC. Tutorial and Applications

R. Bro

Chemometrics and Intelligent Laboratory Systems 1997 - Dimensionality Reduction for Data in Multiple Feature Representations

Y.Y. Lin, T.L. Liu, and C.S. Fuh

Advances in Neural Information Processing Systems 22, 2009 - Denoising and Dimension Reduction in Feature Space

M.L. Braun, K.R. MÃ¼ller, and J.M. Buhmann

Advances in Neural Information Processing Systems 20, 2007 - Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction

H.F. Yu, N. Rao, and I.S. Dhillon

Advances in Neural Information Processing Systems 29, 2016 - Dimensionality Reduction of Massive Sparse Datasets Using Coresets

D. Feldman, M. Volkov, and D. Rus

Advances in Neural Information Processing Systems 29, 2016

**Performance evaluation, hyperparameter selection**

- Image Quality Assessment: From Error Visibility to Structural Similarity

Z. Wang, A. Bovik, et al

IEEE Transactions on Image Processing 2004 - BLEU: a Method for Automatic Evaluation of Machine Translation

K. Papineni, S. Roukos, et al

Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL) 2002 - Random Search for Hyper-Parameter Optimization

J. Bergstra and Y. Bengio

Journal of Machine Learning Research - Practical Bayesian Optimization of Machine Learning Algorithms

J. Snoek, H. Larochelle, and R. Adams

Advances in Neural Information Processing Systems 25, 2012 - "Why Should I Trust You?" Explaining the Predictions of Any Classifier

M.T. Ribeiro, S. Singh, and C. Guestrin

Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

**Missing data, outliers, and anomaly detection**

- Isolation forest {for anomaly detection}

Liu et al

Eighth IEEE International Conference on Data Mining 2008 - Removing Electroencephalographic Artifacts: Comparison between ICA and PCA

T.P. Jung et al

Proceedings of the 1998 IEEE Signal Processing Society Workshop 1998 - Recommender Systems: Missing Data and Statistical Model Estimation

B. Marlin et al

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011) - LOF: Identifying Density-Based Local Outliers

M. Breunig et al

Proceedings of the ACM SIGMOD International Conference on Management of Data 2000 - Support Vector Data Description

D. Tax and R. Duin

Machine Learning 2004 - Anomaly Detection: A Survey

V. Chandola, A. Banerjee, and V. Kumar

ACM Computing Surveys (CSUR), 2009 - Efficient Direct Density Ratio Estimation for Non-stationarity Adaptation and Outlier Detection

T. Kanamori, S. Hido, and M. Sugiyama

Advances in Neural Information Processing Systems 22, 2009

**Miscellaneous**

- Private traits and attributes are predictable from digital records of human behavior

M. Kosinski et al

Proceedings of the National Academy of Sciences 2013 - Learning Fair Representations

R. Zemel et al

Proceedings of the 30th International Conference on Machine Learning 2013 - Data Mining for Internet of Things: A Survey

C.-W. Tsai, C.-F. Lai, and M.-C. Chiang

IEEE Communications Surveys & Tutorials, 16(1) 2014 - Hidden Technical Debt in Machine Learning Systems

D. Sculley et al

Advances in Neural Information Processing Systems 28, 2015 - Meme-tracking and the dynamics of the news cycle

J. Leskovec, L. Backstrom, and J. Kleinberg

Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining 2009 - Theory-guided Data Science: A New Paradigm for Scientific Discovery

A. Karpatne et al

IEEE Transactions on Knowledge and Data Engineering 29 - Matrix Factorization Techniques for Recommender Systems

Y. Koren, R. Bell, and C. Volinsky

Computer, 42(8), 2009 - Mining Internet-Scale Software Repositories

E. Linstead, P. Rigor, and S. Bajracharya

Advances in Neural Information Processing Systems 21, 2008