Deep double descent

OpenAI · 6 years ago · 19

Researchers observed that neural networks including CNNs, ResNets, and transformers exhibit a double descent pattern where performance improves, then deteriorates, then improves again as model size, data size, or training time increases. The effect occurs across multiple architectures and can typically be mitigated through regularization techniques. Understanding the underlying causes of this pattern remains an open research question with implications for model design and training strategies.