MétaCan
Menu
Back to cohort
Record W4315630815 · doi:10.1145/3571243

Type-Preserving, Dependence-Aware Guide Generation for Sound, Effective Amortized Probabilistic Inference

2023· article· en· W4315630815 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.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueProceedings of the ACM on Programming Languages · 2023
Typearticle
Languageen
FieldComputer Science
TopicFormal Methods in Verification
Canadian institutionsUniversity of Waterloo
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsSoundnessInferenceComputer scienceType inferenceProbabilistic logicFuzz testingTheoretical computer scienceProgramming languageExploitMachine learningArtificial intelligence

Abstract

fetched live from OpenAlex

In probabilistic programming languages (PPLs), a critical step in optimization-based inference methods is constructing, for a given model program, a trainable guide program. Soundness and effectiveness of inference rely on constructing good guides, but the expressive power of a universal PPL poses challenges. This paper introduces an approach to automatically generating guides for deep amortized inference in a universal PPL. Guides are generated using a type-directed translation per a novel behavioral type system. Guide generation extracts and exploits independence structures using a syntactic approach to conditional independence, with a semantic account left to further work. Despite the control-flow expressiveness allowed by the universal PPL, generated guides are guaranteed to satisfy a critical soundness condition and moreover, consistently improve training and inference over state-of-the-art baselines for a suite of benchmarks.

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)0.001
metaresearch head score (Gemma)0.021
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.619
Threshold uncertainty score0.987

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.021
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0030.001
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 head0.054
GPT teacher head0.364
Teacher spread0.311 · 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