Oceania
Sparsified SGD with Memory
Sebastian U. Stich, Jean-Baptiste Cordonnier, Martin Jaggi
Several papers consider approaches that limit the number of bits to represent floating point numbers [13, 24, 31]. Recent work proposes adaptive tuning of the compression ratio [7].
Discriminative Calibration: Check Bayesian
However, SBC has drawbacks: The test statistic is somewhat ad-hoc, interactions are difficult to examine, multiple testing is a challenge, and the resulting p-value is not a divergence metric.
Bayesian Optimization with Unknown Search Space
Huong Ha, Santu Rana, Sunil Gupta, Thanh Nguyen, Hung Tran-The, Svetha Venkatesh
Choosing where to search matters. A time-tested path in the quest for new products or processes isthrough experimental optimization.
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
Xinyang Chen, Sinan Wang, Bo Fu, Mingsheng Long, Jianmin Wang
Neural Information Processing Systems http://nips.cc/
Representation Learning for Treatment Effect Estimation from Observational Data
Liuyi Yao, Sheng Li, Yaliang Li, Mengdi Huai, Jing Gao, Aidong Zhang
Neural Information Processing Systems http://nips.cc/
Alleviating Label Switching with Optimal Transport
Pierre Monteiller, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin M. Solomon, Mikhail Yurochkin
Sampling and inference algorithms behave poorly as the number of modes increases, andthisproblem isonlyexacerbated inthiscontextsinceincreasing thenumber ofcomponents in the mixture model leads to a super-exponential increase in the number of modes of the posterior.