Statistical Learning
Streaming Sparse Gaussian Process Approximations
Thang D. Bui, Cuong Nguyen, Richard E. Turner
These authors contributed equally to this work.
Preventing Gradient Explosions in Gated Recurrent Units
Sekitoshi Kanai, Yasuhiro Fujiwara, Sotetsu Iwamura
Neural Information Processing Systems http://nips.cc/
Learning Mixture of Gaussians with Streaming Data
Our main contribution is the first bias-variance bound for the problem of learning Gaussian mixtures with streaming data.
Optimal Shrinkage of Singular Values Under Random Data Contamination
Reconstruction of low-rank matrices from noisy and otherwise contaminated data is a key problem in machine learning, computer vision and data science.
Deep Sets
Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabas Poczos, Russ R. Salakhutdinov, Alexander J. Smola
Neural Information Processing Systems http://nips.cc/
Unsupervised Sequence Classification using Sequential Output Statistics
We show that, compared to earlier works, it is less inclined to be stuck in trivial solutions and avoids the need for a strong generative model.
Hash Embeddings for Efficient Word Representations
Dan Tito Svenstrup, Jonas Hansen, Ole Winther
Our experiments show that hash embeddings can easily deal with huge vocabularies consisting of millions of tokens.
Interactive Submodular Bandit
Lin Chen, Andreas Krause, Amin Karbasi
Neural Information Processing Systems http://nips.cc/
Tensor Biclustering
Soheil Feizi, Hamid Javadi, David Tse
Consider a dataset where data is collected on multiple features of multiple individuals over multiple times.
Trimmed Density Ratio Estimation
Song Liu, Akiko Takeda, Taiji Suzuki, Kenji Fukumizu
Neural Information Processing Systems http://nips.cc/