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

4 results for “Gaussian-Dirichlet”

Gaussian-Dirichlet Posterior Dominance in Sequential Learningstat.ML

Gaussian-Dirichlet posterior dominance proven for sequential categorical data.

problem Sequential learning from categorical observations bounded in [0,1]

method Establishing an ordering between Dirichlet and Gaussian posteriors under N(0,1) noise

result Posterior mean of categorical distribution stochastically dominates Gaussian distribution

sequential learning categorical data posterior dominance Gaussian-Dirichlet

2017-02-14abs ↗pdf ↗

Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observationsstat.ML

Generative model for high-dimensional categorical data using Gaussian-Dirichlet fields.

problem Efficiently modeling and predicting high-dimensional categorical data.

method Combines Dirichlet and Gaussian processes for spatio-temporal modeling.

result Model accurately approximates categorical data in unobserved locations.

Gaussian-Dirichlet fields high-dimensional categorical data spatio-temporal modeling robotics image classification

2020-03-26abs ↗pdf ↗

Sparse and Continuous Attention Mechanismscs.LG

Paper extends sparse alternatives to softmax for continuous domains, enabling efficient attention mechanisms.

problem Efficiently assigning zero probability to irrelevant categories in continuous domains.

method Extend alpha-entmax to continuous domains, introducing continuous-domain attention mechanisms.

result Continuous attention allows attending to time intervals and compact regions, improving text classification, machine translation, and visual question answering.

sparse alternatives softmax continuous domains attention mechanisms Tsallis statistics

2020-06-12abs ↗pdf ↗

Sparse Continuous Distributions and Fenchel-Young Lossescs.LG

This paper develops sparse alternatives to continuous distributions, including new types of Gaussians and attention mechanisms.

problem Creating flexible continuous distributions with varying support for machine learning applications.

method Defining

Ω

-regularized prediction maps and Fenchel-Young losses for arbitrary domains, and deriving new types of Gaussians and attention mechanisms.

result Sparse alternatives to continuous distributions, including deformed exponential families and

β

-Gaussians, are introduced.

sparse distributions continuous domains Fenchel-Young losses Tsallis negentropy attention mechanisms

2021-08-04abs ↗pdf ↗