Unverified50% confidenceFactExact time
研究表明在高维空间中局部最小值往往性能接近全局最优，鞍点才是训练中更大的障碍
1
Sources
50%
Confidence
Long-term
Relevance
8/12/2026
First Seen
Sources
Related Claims
UnverifiedDauphin et al.'s 2014 study showed that difficulties in neural network training mostly arise from saddle points and plateau regions rather than local minima, with the number of saddle points growing exponentially with dimension n.71% similarUnverifiedA 2017 study by Keskar et al. showed that large-batch training tends to converge to sharp minima corresponding to worse generalization, while small-batch training tends toward flat minima.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/735104API
curl https://kongchang.com/api/v1/knowledge/claims/735104MCP
get_claim(id=735104)