MétaCan
Menu
Back to cohort
Record W2952300048 · doi:10.48550/arxiv.1603.04733

Structured and Efficient Variational Deep Learning with Matrix Gaussian\n Posteriors

2016· preprint· en· W2952300048 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenuearXiv (Cornell University) · 2016
Typepreprint
Languageen
FieldComputer Science
TopicGaussian Processes and Bayesian Inference
Canadian institutionsCanadian Institute for Advanced Research
Fundersnot available
KeywordsGaussianMatrix (chemical analysis)Applied mathematicsComputer scienceArtificial intelligenceGaussian processStatistical physicsMathematicsMathematical optimizationMachine learningPhysicsMaterials scienceQuantum mechanics

Abstract

fetched live from OpenAlex

We introduce a variational Bayesian neural network where the parameters are\ngoverned via a probability distribution on random matrices. Specifically, we\nemploy a matrix variate Gaussian \\cite{gupta1999matrix} parameter posterior\ndistribution where we explicitly model the covariance among the input and\noutput dimensions of each layer. Furthermore, with approximate covariance\nmatrices we can achieve a more efficient way to represent those correlations\nthat is also cheaper than fully factorized parameter posteriors. We further\nshow that with the "local reprarametrization trick"\n\\cite{kingma2015variational} on this posterior distribution we arrive at a\nGaussian Process \\cite{rasmussen2006gaussian} interpretation of the hidden\nunits in each layer and we, similarly with \\cite{gal2015dropout}, provide\nconnections with deep Gaussian processes. We continue in taking advantage of\nthis duality and incorporate "pseudo-data" \\cite{snelson2005sparse} in our\nmodel, which in turn allows for more efficient sampling while maintaining the\nproperties of the original model. The validity of the proposed approach is\nverified through extensive experiments.\n

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.872
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.171
Teacher spread0.154 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it