Verified70% confidenceFactExact time
Gradient descent is the most fundamental optimization algorithm in machine learning; a learning rate that is too large causes oscillation, while one that is too small results in slow convergence.
4
Sources
70%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
机器学习入门：如何克服数学焦虑，找到务实的学习路线
Related Claims
UnverifiedMini-batch gradient descent is a compromise between batch and stochastic gradient descent, and is also the most commonly used approach in deep learning frameworks.79% similarUnverifiedNatural gradient descent uses the Fisher information matrix for metric correction of the parameter space and is a theoretical cornerstone of many optimization methods, with applications in variational inference and policy optimization in reinforcement learning.77% similarUnverifiedStochastic gradient descent (SGD) is a cornerstone of machine learning optimization, and rigorous analysis of its convergence rate usually relies on cumbersome probabilistic derivations such as martingale theory or concentration inequalities.74% similarVerifiedGradient descent has spawned three main variants — batch gradient descent, stochastic gradient descent, and mini-batch gradient descent — and the Adam optimizer is a combined improvement built on momentum and adaptive learning rates.74% similarUnverifiedLearning-based methods can achieve very strong performance when annotated data is sufficient, but their robustness degrades significantly when facing domain shift.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/699069API
curl https://kongchang.com/api/v1/knowledge/claims/699069MCP
get_claim(id=699069)