Seminar - Advanced Topics in Machine Learning
Quick Facts
| Organizers: | Jan Peters, Gerhard Neumann, Stefan Roth |
| Default Date: | Friday |
| Default Time: | 15:20 to 17:00 |
| Default Room: | S202 C120 |
| TU-CAN: | 20-00-0804-se Weiterführende Themen im Maschinellen Lernen |
| Credits: | N.A. |
| Mailing List | TBA |
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 19th of October. 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
- 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...
- 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