Unverified50% confidenceFactExact time
List-decodable learning is a relaxed recovery model in statistical learning: the algorithm is allowed to output a candidate list whose size does not exceed a preset upper bound, as long as the target concept appears in the list with high probability.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
Unverified回归、分类、聚类构成传统机器学习的基本任务类型：回归预测连续数值，分类将输入归入离散类别，聚类是无监督学习在无标签情况下发现数据自然分组72% similarVerifiedSpeculative decoding is a lossless acceleration technique that does not alter the model's output distribution; it uses a draft model with far fewer parameters than the target model to generate candidate tokens, which the target model then verifies in parallel.71% similarUnverified自动微分的前向模式适合输入少输出多的场景，反向模式适合输入多输出少的场景，深度学习因参数多而损失为标量属于后者70% similarUnverifiedThis work extends classical concentration inequalities to the data-dependent setting, providing theoretical tools for scenarios such as reinforcement learning and sequential decision-making.69% similarUnverifiedBatch inference refers to passing multiple independent tasks in a single model call at the same time, where the model must return results corresponding one-to-one with the inputs, which differs from the concept of batch size in traditional machine learning.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098117API
curl https://kongchang.com/api/v1/knowledge/claims/1098117MCP
get_claim(id=1098117)