Sample-complexity bound for high-order linear systems
Produced by Long-Context Linear System Identification
Empirical risk minimization
A learning rule that selects a predictor by minimizing average loss over observed data within a specified hypothesis class.
A learning rule that selects a predictor by minimizing average loss over observed data within a specified hypothesis class.
Its statistical behavior depends on the loss, hypothesis class, data-generating process, and optimization assumptions.
Connections
Has applicable result
Sample-complexity bounds for next-token prediction
Produced by On the Sample Complexity of Next-Token Prediction