On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “DLDA”

Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMCstat.ML

A new method for scalable inference in deep discrete LVMs.

problem Challenges in scalable inference for deep discrete latent variable models.

method Topic-layer-adaptive stochastic gradient Riemannian MCMC (TLASGR) for DLDA.

result State-of-the-art results on big data sets.

Deep Latent Dirichlet Allocation DLDA Stochastic Gradient MCMC Topic-Layer-Adaptive Riemannian

2017-06-06abs ↗pdf ↗

Gene Expression based Survival Prediction for Cancer Patients: A Topic Modeling Approachcs.LG

Novel topic modeling approach improves survival prediction for cancer patients.

problem Survival prediction for cancer patients using high-dimensional gene expression data.

method Inspired by topic modeling, a novel methodology using discretized Latent Dirichlet Allocation (dLDA) to derive expressive features from gene expression data.

result Survival estimates are more accurate than standard models, as shown by the Concordance measure.

cancer gene expression survival prediction topic modeling discretized LDA

2019-03-25abs ↗pdf ↗