Unverified50% confidenceFactExact time
Gunasekar等在2017年在矩阵分解问题上证明梯度下降倾向于收敛到核范数最小的解
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
The Theory of Deep Learning: Why Do Neural Networks Work? A Complete Overview of Theoretical Research
hackernewshackernews7/11/2026
Related Claims
UnverifiedSmaller models often show exponential rather than linear degradation in performance on long reasoning chain tasks.66% similarUnverifiedLow-rank decomposition and quantization compression are orthogonally complementary dimensions; quantizing the smaller matrices A and B separately results in smaller errors, and the combined compression ratio can reach several times that of either method alone65% similarUnverifiedGradient descent mathematically involves partial derivatives and the chain rule, and its intuitive essence is a 'downhill' process of finding the lowest point.65% similarUnverifiedRNNs face the vanishing gradient problem: the longer the sequence, the longer the chain of multiplications the gradient must pass through, causing values to shrink exponentially.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/494295API
curl https://kongchang.com/api/v1/knowledge/claims/494295MCP
get_claim(id=494295)