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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “mean-parametrization”

A solution for the mean parametrization of the von Mises-Fisher distributionstat.CO

We solve the mean parametrization of von Mises-Fisher distribution.

problem No closed-form normalization function for mean parameters exists.

method Derived a second-order ODE for mean normalizer and provided approximations.

result Rapid evaluation of densities and natural parameters in terms of mean parameters.

von Mises-Fisher distribution mean parametrization maximum-likelihood estimation Bregman Clustering topic modeling

2024-04-10abs ↗pdf ↗

Bayesian Mean-parameterized Nonnegative Binary Matrix Factorizationstat.ML

Unified Bayesian NMF models for binary data with automatic dimension selection.

problem Binary data analysis with nonnegative matrix factorization and link functions.

method Bayesian mean-parameterized nonnegative binary matrix factorization (NBMF) models with collapsed Gibbs and variational algorithms.

result Automatic detection of relevant components without manual tuning.

Bayesian NMF nonnegative matrix factorization binary data mean-parametrization collapsed Gibbs sampler

2018-12-17abs ↗pdf ↗

Variational Representations of Annealing Paths: Bregman Information under Monotonic Embeddingcs.LG

New analysis of annealing paths in sampling and estimation.

problem Sampling from complex distributions and estimating normalization constants.

method Extending known results on Bregman divergence to quasi-arithmetic means under monotonic embedding.

result Analogous result for quasi-arithmetic means, highlighting the interplay between means, parametric families, and divergence functionals.

Annealing Paths Markov Chain Monte Carlo Bregman Divergence Quasi-Arithmetic Means Monotonic Embedding

2022-09-15abs ↗pdf ↗

A majorization-minimization algorithm for nonnegative binary matrix factorizationcs.LG

Paper proposes an efficient algorithm for nonnegative binary matrix factorization.

problem Decomposing binary data using matrix factorization.

method Majorization-minimization algorithm with Beta prior for improved performance.

result Proposed algorithm offers excellent trade-off between performance, complexity, and interpretability.

binary matrix factorization majorization-minimization Beta prior maximum a posteriori matrix completion

2022-04-20abs ↗pdf ↗