Statistical Learning
Stochastic Optimization with Laggard Data Pipelines
State-of-the-art optimization is steadily shifting towards massively parallel pipelines with extremely large batch sizes.
Stochastic Optimization with Laggard Data Pipelines
State-of-the-art optimization is steadily shifting towards massively parallel pipelines with extremely large batch sizes.
Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections
Matthew Lawlor, Steven W. Zucker
Neural Information Processing Systems http://nips.cc/
An Unbiased Risk Estimator for Learning with Augmented Classes
The main challenge of the LAC problem lies in how to depict relationships between known and augmented classes.
Approximate Gaussian process inference for the drift function in stochastic differential equations
Andreas Ruttor, Philipp Batz, Manfred Opper
We introduce a nonparametric approach for estimating drift functions in systems of stochastic differential equations from sparse observat ions of the state vector. Using a Gaussian process prior over the drift as a function of the state vector, we develop an approximate EM algorithm to deal with the unobser ved, latent dynamics between observations. The posterior over states is appr oximated by a piecewise linearized process of the Ornstein-Uhlenbeck type and the M AP estimation of the drift is facilitated by a sparse Gaussian process regressio n.
Dimensionality reduction: theoretical perspective on practical measures
Yair Bartal, Nova Fandina, Ofer Neiman
Dimensionality reduction plays a central role in real world applications for Machine Learning, among many fields.
