(subjectif; à consolider)
Tutorials
- Langford, Structured prediction. http://www.hunch.net/~l2s/
Invited talk: Bottou +++
- 2 learning modules in interaction (one explores, one classifies): misleading effects (exploration results are bad on average, therefore no need to explore, we were right the first time)
- test: must be reconsidered. (consider the tails of distribution and coverage)
Top Papers
- Unsupervised Domain Adaptation by Backpropagation Yaroslav Ganin, Victor Lempitsky
- two objectives on features: being discriminative wrt class; not discriminant wrt source/target
- Learning Transferable Features with Deep Adaptation Networks Mingsheng Long, Yue Cao, Jianmin Wang, Michael Jordan
- related to the previous + kernels.
OK Papers
- Strongly Adaptive Online Learning Amit Daniely, Alon Gonen, Shai Shalev-Shwartz
- Online and adaptive weights on experts + intervals + doubling trick
- Adaptive Belief Propagation Georgios Papachristoudis, John Fisher
- Question for me: why not considering several spanning trees...
Papiers anciens que j'avais manqués
- Label-Embedding for Attribute-Based Classification (embarrassingly simple).