← All concepts

training optimization

2 articles · 3 co-occurring · 0 contradictions · 99 briefs

Listwise 损失 vs Pointwise BCE：+30.7pp（后者在高度同质池中失效）" — The comparison between Listwise loss and Pointwise BCE reveals a significant 30.7pp improvement and identifies a failure mode of BCE in homogeneous

Related concepts
retrieval ranking pipeline 1 ranking systems 1 hyperparameter optimization 1
Signal history
2026-W30
12
2026-W29
14
2026-W28
14
2026-W27
10
2026-W26
6
2026-W25
14
2026-W24
14
2026-W23
8
2026-W22
14
2026-W21
12
2026-W20
14
2026-W19
10
Evidence chain (2 articles, showing 2)
@shao__meng: 两阶段 retrieve-and-rerank 流水线，总参数仅 1.2B（0.6B 编码器 + 0.6B 重排序器），专为消费级硬件设计。 extends

Listwise 损失 vs Pointwise BCE：+30.7pp（后者在高度同质池中失效）" — The comparison between Listwise loss and Pointwise BCE reveals a significant 30.7pp improvement and identifies a failure mode of BCE in homogeneous

@vivek_2332: definitely agree. the concept of autoresearch isn't new, letting llms optimiz... extends

for weight matrices the frobenius norm gradient (what adam and sgd use) is geometrically wrong. the "correct" steepest descent direction for a weight matrix is the one that minimizes the loss subject

query this concept
$ db.articles("training-optimization")
$ db.cooccurrence("training-optimization")
$ db.contradictions("training-optimization")