Unverified50% confidenceFactExact time
The standard federated aggregation algorithm FedAvg assumes that client gradients can be directly averaged to estimate the global gradient, but simple averaging under Non-IID conditions causes gradient drift.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe mean-field likelihood estimation relied upon by existing RL methods for diffusion models is biased and has high variance.60% similarUnverifiedResearch by Gunasekar et al. in 2017 proved that for linear models, gradient descent is equivalent to minimum-norm interpolation.60% similarUnverifiedThe algorithm employs variance-reduced estimation of the Bellman optimality operator locally at each agent.59% similarUnverified测试时计算扩展的边际收益并非线性，存在明显的收益递减区间59% similarUnverifiedAssuming the data follows a Gaussian distribution, maximizing the likelihood is equivalent to minimizing the mean squared error.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001324API
curl https://kongchang.com/api/v1/knowledge/claims/1001324MCP
get_claim(id=1001324)