Reading group on Machine Learning
The Machine Learning group organizes weekly meetings to discuss papers/topic relevant to the field of ML. Here you can find information on the meeting format, schedule, papers and presenters.
Usually all the Thurdays, starting at 11 am. When the guidelines will allow again, the meetings will take places in the Fourier Meeting Room (at EURECOM). Until then, the reading group will be online. Contact Dimitrios Milios for the link to the conference call.
Areas of Interest
Machine learning, statistical modeling, Bayesian inference (variational inference, MCMC, etc.), Deep learning theory (generalization bounds, optimization, etc.), computer vision, biomedical image/data analysis, etc.
At each meeting, there will be a presenter who will be responsible for leading the discussion of a paper. The paper will be chosen by the presenter and posted here about a week before the corresponding meeting. The presentation format is completely free: slides are welcome but you can rely on the whiteboard to illustrate ideas, equations, etc. Participants should come to the meeting with the paper either printed out or available on a portable device. Participants are strongly encouraged to read the paper beforehand, thus being ready for the discussion.
Here are some guidelines for the presenter, who should come to the meeting with answers to each of these questions.
- What problem is the paper addressing? Is this an interesting mathematical problem? At a very high level, is this a classical mathematical problem? Are there classical solutions (e.g., something you can find on wikipedia) that you can think of?
- What other state-of-the-art methods/algorithms (say published in last 3-5 years) are out there that address the same/similar problem? Do authors run benchmarking experiments (i.e. empirical comparisons)?
- What is the application the authors choose (if any)? Is this an interesting application? What was lacking for existing solutions? Were they too slow? Maybe they didn’t really solve the problem exactly?
- What’s wrong with the proposed method? What are the acknowledged/unacknowledged weaknesses?
- How can the proposed method be improved? What are the natural future directions of research? Are there new applications you can think of?
- What would you do differently if you approached this problem?
- What is the core innovation and contribution of this paper? Is it a mathematical derivation? If so, can you point to it and understand the steps? Was there a far-reaching theoretical result/insight? If so, can you summarize? Was there a novel empirical finding? Is there an accompanying open software package that others can pick up and use on their own data/problem?
These guidelines are inspired by the journal club organized by the Sabuncu Lab at Cornell University.