Memorizing without overfitting: Bias, variance, and interpolation in overparameterized models
The bias-variance trade-off is a central concept in supervised learning. In classical statistics, increasing the complexity of a model (e.g., number of parameters) reduces bias but also increases variance. Until recently, it was commonly believed that optimal performance is achieved at intermediate...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Physical Society
2022-03-01
|
| Series: | Physical Review Research |
| Online Access: | http://doi.org/10.1103/PhysRevResearch.4.013201 |