Seminar - Advanced Topics in Machine Learning

Quick Facts

Abstract

The seminar concentrates on reviewing the latest developments in machine learning by reviewing topics and papers from the last few NIPS, ICML and AISTATS conferences. The seminar is focused on PhD students but outstanding master students are also welcome to join. There will be different topics presented by groups of 2 - 3 team members. The presentation of each topic should take approximately 60 - 90 minutes and should also include a review of the relevant background that are needed to understand the presented topics. PhD students should present once a year (every second semester).

Topics

Each participant is asked to send at least 3 topics he is interested to Jan Peters by Monday the 4th of May. We will then assign the teams, where each master student will be paired with a post-doc who will become his "coach" for the presentation. You can choose from the following topics:

• Reproducing Kernel Hilbert Spaces: Papers from: A. Gretton, K. Fukumizu, L. Song
• Deep Neural Networks: Work from Bengio, Hinton, etc... Could be multiple sub-topics
• Structured Prediction: Work from H. Daume, Drew Bagnell
• (Stochastic) Variational Inference: Work from D. Blei
• Sampling for Bayesian Learning: Work on Slice Sampling and papers by Max. Welling (Fisher scoring)
• Recent advances for GPs and Local Regression Methods: Phillip Henning and Titsias
• Recent work on Bandits, Linear Bandits: G. Neu, O. Maillard, R. Munos...
• Recent work Decision and Regression Trees: Have to search for papers...
• Recent work on Boosting: Have to search for papers...
• Sampling by Optimization: Papers by G. Papandreo, Jaakkola, Tom Minka, Max Welling
• Bounds in Reinforcement Learning: C. Csevaspari, R, Munos
• Copula's: Have to search for papers...
• Causality: Have to search for papers...
• New Developments in Stochastic Gradient Descent: Papers by F. Bach
• Online Learning

Selections

• Hany Abdusalmed: Bounds in Reinforcement Learning, Recent work on Bandits, Linear Bandits, (Stochastic) Variational Inference
• Oleg Arenz: Structured Prediction, Reproducing Kernel Hilbert Spaces, Deep Neural Networks
• Tom Friedrich Buchholz: Deep Neural Networks, Structured Prediction, Recent work on (linear) Bandits
• Roberto Calandra: Deep learning, Online learning, Variational Inference / Causality [Prefers to present in winter semester due to internship].
• Tobias Croon: Deep Neural Networks, Structured Prediction, (Stochastic) Variational Inference.
• Marco Ewerton: Deep Neural Networks, Reproducing Kernel Hilbert Spaces, (Stochastic) Variational Inference [Prefers to present in winter semester].
• Jochen Gast: Stochastic Variational Inference, Using Discrete Optimization to Learn and Sample from Energy Models, Deep Neural Networks
• Gregor Gebhardt: Deep Neural Networks, Stochastic Variational Inference, Sampling for Bayesian Learning [Prefers to present in winter semester]
• Heiko Guckes: Deep Neural Networks (Work from Bengio, Hinton, etc... Could be multiple sub-topics), Sampling for Bayesian Learning (Work on Slice Sampling and papers by Max. Welling on Fisher scoring), Recent work on Boosting (Have to search for papers...)
• Jan-Hendrik Lange: Sampling by Optimization, Stochastic Gradient Descent, (Linear) Bandits
• Alex Paraschos: Structured Prediction, Reproducing Kernel Hilbert Spaces, Variational Inference [winter]
• Riad Akrour: Sampling by Optimization, Recent advances for GPs and Local Regression Methods, (Stochastic) Variational Inference
• Takayuki Osa: Deep Neural Networks, Reproducing Kernel Hilbert Spaces, (Stochastic) Variational Inference [Prefers to present in winter semester]
• Oliver Kroemer: Deep Learning, Sampling for Bayesian Learning, Reproducing Kernel Hilbert Spaces, Structured Prediction
• Filipe Veiga: Deep learning, (Stochastic) Variational Inference, Reproducing Kernel Hilbert Spaces, copula's/causality [prefer winter semester].
• Simone Parisi: Deep Learning, Recent Work on Bandits, Reproducing Kernel Hilbert Spaces [Winter]
• Herke van Hoof: Stochastic variational inference, Sampling, Structured prediction, Reproducing kernel hilbert spaces [winter]
• Christian Daniel: Recent work Decision and Regression Trees, Structured Prediction, Deep Neural Networks [Winter]
• Rudolf Lioutikov: (Stochastic) Variational Inference, Recent work on Bandits, Deep Neural Networks [Winter]
• Tobias Plötz: Stochastic Variational Inference, Sampling by Optimization, Recent work Decision and Regression Trees

Schedule