Anthropic·Software Engineer·Take-home Assignment
- Design and run an experiment that reproduces sample-wise double descent, where test error peaks near the interpolation threshold and then decreases again as the model-to-data ratio crosses it.
- Provide a theoretical explanation for why double descent occurs, using the bias-variance decomposition of the least-squares estimator and the behavior of the design matrix spectrum near the interpolation threshold.
- Propose and demonstrate a method to mitigate the double descent peak, both experimentally and analytically.
“Linear regression with varying sample count is the obvious setup and I went with it.”