Unverified50% confidenceFactExact time
For the unconstrained hypothesis class, the relationship between the prediction error of MLIPs and sampling accuracy is exponentially ill-posed in terms of dimensionality: even if the prediction errors of energy and forces decay exponentially with dimensionality, the total variation distance between the learned distribution and the target distribution may still approach its maximum value.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe excess risk bound measures the risk gap between the predictor obtained by the learning algorithm and the optimal predictor within the hypothesis space, and typically consists of two parts: estimation error and approximation error.79% similarUnverified研究团队证明学习分布与真实分布之间的总变差距离可分解为初始化误差、Score误差和求解器离散化误差三项77% similarUnverifiedTotal prediction error can be decomposed into bias² + variance + irreducible error.76% similarUnverifiedThe cost of the theoretical consistency of the importance-weighted version is that the weights may have large variance, and when the model-generated distribution differs greatly from the target distribution, the weights become extreme, leading to unstable training.76% similarUnverifiedThis approximation error is independent of model capacity: even with a perfect marginal distribution predictor trained on infinite data, the product approximation will inevitably deviate from the joint distribution when writing to multiple positions with dependencies in parallel.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029463API
curl https://kongchang.com/api/v1/knowledge/claims/1029463MCP
get_claim(id=1029463)