Unverified50% confidenceFactExact time
The classic gradient attribution method TracIn estimates influence by computing the inner product between the gradient of a training sample and that of a test sample, but it requires a separate backpropagation for each sample, and its computational complexity grows linearly with data size, making it hard to apply to million-scale datasets.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedGradient accumulation accumulates gradients over multiple small batches before performing a single parameter update, with an effect equivalent to training with a large batch.70% similarUnverifiedIn long-cycle training, even if one-thousandth of samples are misaligned per epoch, after accumulating over tens of thousands of steps it may significantly change the model's convergence path, making experimental results under different resource schedules lose comparability.70% similarUnverifiedHigh-dimensional structure learning of Gaussian DAGs faces a statistical-computational gap: methods with sharp sample complexity rely on computationally expensive subset searches and require a pre-specified in-degree upper bound, while polynomial-time algorithms exhibit comparatively inferior sample complexity.69% similarUnverifiedLarge-scale rollout generation requires high-throughput inference capability, while the training stage requires substantial compute, and switching and allocating between the two within the same cluster is the core challenge.67% similarUnverified批量梯度下降使用全部训练数据计算梯度，随机梯度下降每次只用一个样本，小批量梯度下降在两者之间取得平衡66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105867API
curl https://kongchang.com/api/v1/knowledge/claims/1105867MCP
get_claim(id=1105867)