Weighted loss for different assets
Question
You train on a panel of stocks with widely different volatility. What changes when squared errors are weighted by inverse variance?
Short answer
The model prioritises errors relative to the assumed noise scale rather than equally weighting errors in raw return units. This can improve statistical efficiency under a correct conditional variance model, but changes the economic objective and may overemphasise very low estimated variances. Estimate weights from information available at training time, regularise or cap extreme weights, and evaluate the intended portfolio-level outcome.
Original question and answer written by SelfMadeQuant.com.
See the hint and the full worked solution in the question bank (free account).
Open the worked solutionLessons behind this question
- Ridge, Lasso, and Elastic Net
- The Normal Equations: Closed-Form Least Squares
- Covariance and Correlation
Start with a free lesson: Expectation, Variance and Covariance is part of a free topic. Create a free account, no card needed, to read it in full with worked solutions.
Read it free