Unverified50% confidenceFactExact time
Double Descent refers to the phenomenon where over-parameterized neural networks should theoretically suffer from severe overfitting but in practice exhibit good generalization ability, and it remains an active area of research.
1
Sources
50%
Confidence
Long-term
Relevance
8/13/2026
First Seen
Sources
泛化才是机器学习的核心：训练前决定成败的关键因素
Related Claims
Unverified双重下降现象为OpenAI等机构提出的神经网络缩放定律（Scaling Laws）提供了理论基础70% similarUnverifiedGradient descent is essentially a combination of calculus and optimization theory.64% similarUnverifiedThe core of gradient-based learning is continuous optimization; the neural network parameter space is a high-dimensional real-number space and the loss function is approximately differentiable64% similarUnverifiedVanishing gradient refers to the exponential decay of gradient values during backpropagation in deep neural networks, causing parameters near the input layer to receive almost no updates.63% similarUnverified传统梯度下降方法（如SGD、Adam）要求目标函数可微且连续，在面对离散、非凸、多模态问题时容易陷入局部最优62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/740638API
curl https://kongchang.com/api/v1/knowledge/claims/740638MCP
get_claim(id=740638)