Asia
Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation
In this paper, we present MixV al, an innovative model selection method that operates solely with unlabeled target data during inference.
Deep Generative Markov State Models
Hao Wu, Andreas Mardt, Luca Pasquali, Frank Noe
We propose a deep generative Markov State Model (DeepGenMSM) learningframework for inference of metastable dynamical systems and prediction of tra-jectories.
GraphStructuredPredictionEnergyNetworks
Specifically,GSPENs combine thecapabilities ofclassicalstructured prediction models andSPENs andhavetheability toexplicitly model localstructure whenknown or assumed, while providing the ability to learn an unknown or more global structure implicitly.
KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training
This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of
Double Quantization for Communication-Efficient Distributed Optimization
Yue Yu, Jiaxiang Wu, Longbo Huang
Modern distributed training of machine learning models often suffers from high communication overhead for synchronizing stochastic gradients and model parameters.
Using Large Ensembles of Control Variates for Variational Inference
Neural Information Processing Systems http://nips.cc/
A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization
Sulaiman Alghunaim, Kun Yuan, Ali H. Sayed
Neural Information Processing Systems http://nips.cc/
TopRank: A practical algorithm for online stochastic ranking
Tor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvari
Neural Information Processing Systems http://nips.cc/