Andrew Koh

Oct 31, 2024 | arxiv.org | Andrew Koh

arXiv:2410.24191 (econ) View PDF HTML (experimental) Subjects: Theoretical Economics (econ.TH); Computer Science and Game Theory (cs.GT) Cite as: arXiv:2410.24191 [econ.TH] (or arXiv:2410.24191v1 [econ.TH] for this version) https://doi.org/10.48550/arXiv.2410.24191 Submission history From: Andrew Koh [ view email] [v1] Thu, 31 Oct 2024 17:51:10 UTC (1,564 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle Connected Papers (What is Connected...

Feb 11, 2024 | biorxiv.org | Vanessa Kennedy |Ritu Roy |Cheryl Peretz |Andrew Koh

AbstractMotivationRecently, single cell DNA sequencing (scDNAseq) and multimodal profiling with the addition of cell surface antibodies (scDAbseq) have provided key insights into cancer heterogeneity. Scaling these technologies across large patient cohorts, however, is cost and time prohibitive. Multiplexing, in which cells from unique patients are pooled into a single experiment, offers a possible solution.

Nov 4, 2023 | biorxiv.org | Shidan Wang |Yiqing Wang |Ruichen Rong |Andrew Koh

AbstractRecent technological advances have highlighted the significant impact of the human microbiome and metabolites on physiological conditions. Integrating microbiome and metabolite data has shown promise in predictive capabilities. We developed a new supervised contrastive learning framework, MB-SupCon-cont, that (1) proposes a general contrastive learning framework for continuous outcomes and (2) improves prediction accuracy over models using single omics data.

Apr 25, 2023 | researchgate.net | Andrew Koh

Jointly learning from a small labeled set and a larger unlabeled set is an active research topic under semi-supervised learning (SSL). In this paper, we propose a novel SSL method based on a two-stage framework for leveraging a large unlabeled in-domain set. Stage-1 of our proposed framework focuses on audio-tagging (AT), which assists the sound event detection (SED) system in Stage-2.

Mar 21, 2023 | news.yale.edu | Mike Cummings |Andrew Koh

When archaeological scientist Andrew Koh unearths a dusty artifact, say a clay pot or alabaster jar, the last thing he’ll do is clean it. Archaeologists routinely wash artifacts soon after excavating them to examine their ornamentation and style. For Koh, the dirt and grime could yield evidence of humanity’s past just as exciting as the objects themselves.