Conference Paper - page 3

Scalable Adaptive Stochastic Optimization Using Random Projections

Phase Transitions in Parameter Rich Optimization Problems

Model Selection for Gaussian Process Regression

MRI-Based Surgical Planning for Lumbar Spinal Stenosis

Guarantees for Greedy Maximization of Non-submodular Functions with Applications

Guaranteed Non-convex Optimization: Submodular Maximization over Continuous Domains

TI-Pooling: Transformation-invariant pooling for feature learning in convolutional neural networks

Information-theoretic analysis of MaxCut algorithms

NP-hard combinatorial optimization algorithms are often characterized by their approximation ratios. In real world applications, the resilience of algorithms to input fluctuations and to modelling errors pose important robustness requirements. This work suggests a provable algorithmic regularization and validation strategy based on posterior agreement. The strategy regularizes algorithms and ranks them according to the informativeness of their output given noisy input. To illustrate this strategy, we develop methods to evaluate the posterior distribution of the Goemans-Williamson's MaxCut algorithm using semidefinite...

Inferring Non-linear State Dynamics using Gaussian Processes

Visual saliency based active learning for prostate MRI segmentation