Model reduction of linear dynamical systems via balancing for Bayesian inference

Keyphrases

• Linear Dynamical Systems 100%
• Bayesian Inference 100%
• Model Reduction 100%
• Gramian 75%
• Dynamical Systems 50%
• Dimensionality Reduction 50%
• Covariance 50%
• Covariance Approximation 50%
• Balanced Truncation 50%
• Order of Magnitude 25%
• Benchmark Problems 25%
• Computational Tools 25%
• Near-optimal 25%
• Bayesian Approach 25%
• Large Dimension 25%
• Reachability 25%
• Reduced Model 25%
• Output Measurement 25%
• Computational Burden 25%
• Noisy Output 25%
• Stability Properties 25%
• Posterior Mean 25%
• Inference Problem 25%
• Truncation Method 25%
• System Operator 25%
• System State 25%
• Error Bound 25%
• Natural Connection 25%
• Fisher Information 25%
• Gaussian Process Inference 25%
• Observability Gramian 25%
• Reachability Gramian 25%
• Reduced Dynamical System 25%
• State Dimension 25%
• Exact Posterior Distribution 25%

Mathematics

• Linear Dynamical Systems 100%
• Covariance 100%
• Bayesian Inference 100%
• Dynamical System 75%
• Truncation 50%
• Approximates 25%
• Gaussian Distribution 25%
• Initial Condition 25%
• Reduced Model 25%
• Bayesian Approach 25%
• Posterior Distribution 25%
• Posterior Mean 25%
• Error Bound 25%
• Theoretic Approach 25%
• Fisher Information 25%
• System State 25%
• Theoretic System 25%
• Initial Time 25%

Engineering

• Model Reduction 100%
• Observability 50%
• Reachability 50%
• Balanced Truncation 50%
• Initial Condition 25%
• Gaussians 25%
• Bayesian Approach 25%
• Benchmark Problem 25%
• System Operator 25%
• System State 25%
• Posterior Distribution 25%
• Error Bound 25%
• Fisher Information 25%
• Initial Time 25%