Statistical Learning
Robust Learning of Fixed-Structure Bayesian Networks
Yu Cheng, Ilias Diakonikolas, Daniel Kane, Alistair Stewart
In this work, we study the fully observable discrete case where the structure of the network is given.
Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
Thomas George, Cรฉsar Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent
Stochastic Gradient Descent (SGD) and its variants are the current workhorse for training neural networks.
But How Does It Work in Theory? Linear SVM with Random Features
Yitong Sun, Anna Gilbert, Ambuj Tewari
Neural Information Processing Systems http://nips.cc/
Low-Rank Tucker Decomposition of Large Tensors Using TensorSketch
Osman Asif Malik, Stephen Becker
Neural Information Processing Systems http://nips.cc/
Communication Compression for Decentralized Training
Hanlin Tang, Shaoduo Gan, Ce Zhang, Tong Zhang, Ji Liu
When workers cannot form a fully connected communication topology or the communication latency is high (e.g., in
Large Margin Deep Networks for Classification
Gamaleldin Elsayed, Dilip Krishnan, Hossein Mobahi, Kevin Regan, Samy Bengio
Such methods are therefore not well suited for deep networks. In this work, we propose a novel loss function to impose a margin on any chosen set of layers of a deep network (including input and hidden layers).
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo
Marton Havasi, Josรฉ Miguel Hernรกndez-Lobato, Juan Josรฉ Murillo-Fuentes
Neural Information Processing Systems http://nips.cc/
Processing of missing data by neural networks
Marek ลmieja, ลukasz Struski, Jacek Tabor, Bartosz Zieliลski, Przemysลaw Spurek
We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron's response in the
The Cluster Description Problem - Complexity Results, Formulations and Approximations
Ian Davidson, Antoine Gourru, S Ravi
There are many clustering algorithms which perform well towards their aim of finding cohesive groups of instances.
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
Blake E. Woodworth, Jialei Wang, Adam Smith, Brendan McMahan, Nati Srebro
In an oracle model, we place limits on the algorithm's access to the optimization