An Interdepartmental Research Center
Committed to Advancing the Analytical Information and Decision Sciences.

Upcoming LIDS Events

July

26

LIDS Thesis Defense

Reduction Methods in Semidefinite...

32-D677

1:00pm
July

31

LIDS Thesis Defense

Latent Variable Model Estimation...

32-G449

2:00pm

LIDS Research Highlights

Camera Control for Learning Nonlinear Target Dynamics via Bayesian Non-Parametric Dirichlet-Process Gaussian-Process (DPGP) Models

Mobile sensors are often deployed to cooperatively perform surveillance of an environment and track objects of interest: for example, intrusion detection throughout a secure facility, and anomaly detection in manufacturing plants. In many such cases it is infeasible to provide accurate sensor coverage of the entire environment, and thus an environment model and associated controller that accounts for sensor field-of-view (FoV) geometry is necessary to determine sensor configurations that minimize uncertainty.

Lifts of polytopes and matrix factorization

Linear programming is an ubiquitous technique used in a wide variety of disciplines, ranging from scheduling and planning in management, to signal processing and control theory in engineering. From a mathematical point of view, linear programming is the problem of maximizing a linear function over a polytope. In order to solve such an optimization problem in practice, it is important to have a concise description of the polytope under consideration. Consider for example the hexagon depicted in Figure 1 (left), which is a simple example of a polytope.

Approximate Decentralized Bayesian Inference

Recent trends in the growth of datasets, and the methods by which they are collected, have led to increasing interest in the parallelization of machine learning algorithms. Parallelization results in reductions in both the memory usage and computation time of learning, and allows data to be collected and processed by a network of learning agents rather than by a single central agent.