133 citations · 192 across the 9 of their papers we have counts for
8 papers · 1 filter
Stochastic Control with Affine Dynamics and Extended Quadratic Costs
Shane Barratt, Stephen Boyd
An extended quadratic function is a quadratic function plus the indicator function of an affine set, that is, a quadratic function with embedded linear equality constraints. We sho…
Learning Probabilistic Trajectory Models of Aircraft in Terminal Airspace from Position Data
Shane Barratt, Mykel Kochenderfer, Stephen Boyd
Models for predicting aircraft motion are an important component of modern aeronautical systems. These models help aircraft plan collision avoidance maneuvers and help conduct offl…
Improved Training with Curriculum GANs
Rishi Sharma, Shane Barratt, Stefano Ermon +1
In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the co…
Optimizing for Generalization in Machine Learning with Cross-Validation Gradients
Shane Barratt, Rishi Sharma
Cross-validation is the workhorse of modern applied statistics and machine learning, as it provides a principled framework for selecting the model that maximizes generalization per…
A Matrix Gaussian Distribution
Shane Barratt
In this note, we define a Gaussian probability distribution over matrices. We prove some useful properties of this distribution, namely, the fact that marginalization, conditioning…
On the Differentiability of the Solution to Convex Optimization Problems
Shane Barratt
In this paper, we provide conditions under which one can take derivatives of the solution to convex optimization problems with respect to problem data. These conditions are (roughl…