A closed-form matrix regularization parameter for ℓ1-regularized Gaussian MLE, obtained by fixing reselection probability of nonzero entries, matches CV accuracy and support recovery at far lower cost.
A network-centric hardware/algorithm co-design to accelerate distributed training of deep neural networks
5 Pith papers cite this work, alongside 25 external citations. Polarity classification is still indexing.
5
Pith papers citing it
25
external citations · external index
citation-role summary
background 2
citation-polarity summary
years
2026 5roles
background 2representative citing papers
DBLP dynamically bounds gradient loss by training phase, cutting end-to-end training time ~24% on average and up to 5.88× single-round latency under microbursts versus a SOTA baseline.
History-based and runtime-dependency-based change impact recommendations for JavaScript overlap only 22% at a 60-function inspection budget, so hybrid recommendations cover more relevant candidates than either signal alone.
A qualitative study maps emotions exploited by financial scammers and help-seeking needs at different scam stages, identifying risk factors and suggesting design implications for interventions.
Systematic literature review synthesizing seven research streams on formal grammars in BPM and five corpus-grounded open challenges for cross-stream integration.
citing papers explorer
-
The Regularization Parameter: Sparse Precision Matrix Estimation
A closed-form matrix regularization parameter for ℓ1-regularized Gaussian MLE, obtained by fixing reselection probability of nonzero entries, matches CV accuracy and support recovery at far lower cost.
-
DBLP: Phase-Aware Bounded-Loss Transport for Burst-Resilient Distributed ML Training
DBLP dynamically bounds gradient loss by training phase, cutting end-to-end training time ~24% on average and up to 5.88× single-round latency under microbursts versus a SOTA baseline.
-
Change Impact Recommendation for JavaScript: Lessons from History and Runtime Analysis
History-based and runtime-dependency-based change impact recommendations for JavaScript overlap only 22% at a 60-function inspection budget, so hybrid recommendations cover more relevant candidates than either signal alone.
-
"It didn't feel right but I needed a job so desperately": Understanding People's Emotions & Help Needs During Financial Scams
A qualitative study maps emotions exploited by financial scammers and help-seeking needs at different scam stages, identifying risk factors and suggesting design implications for interventions.
-
Formal Grammars in Business Process Management: A Systematic Literature Review
Systematic literature review synthesizing seven research streams on formal grammars in BPM and five corpus-grounded open challenges for cross-stream integration.