Unverified50% confidenceFactExact time
The optimization problem of weighted MMD is non-convex, and when the number of particles is insufficient, gradient flow easily falls into spurious local minima.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the field of weighted MMD optimization, previous results on overparameterized benign landscapes were mostly concentrated in neural networks or specific non-convex problems, and the corresponding theory for MMD particle optimization has remained a blank.76% similarUnverifiedFor any compactly supported target distribution, as long as the number of particles is sufficiently large, the MMD at every local minimum in the weighted MMD optimization landscape can be arbitrarily small.74% similarUnverifiedWhen the target distribution has finite support, the paper gives an explicit particle count threshold, beyond which no spurious local minima exist and every spurious stationary point is unstable.73% similarUnverified浮点数在token空间中并非连续分布，导致LLM精确运算天然不可靠71% similarUnverifiedUnder weight-free gradient flow, any stationary point whose MMD value is far from zero is unstable, and gradient flow will not stably remain at these bad stationary points.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037441API
curl https://kongchang.com/api/v1/knowledge/claims/1037441MCP
get_claim(id=1037441)