MétaCan
Menu
Back to cohort
Record W4405467872 · doi:10.3934/fods.2024053

Deep learning with Gaussian continuation

2024· article· en· W4405467872 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

VenueFoundations of Data Science · 2024
Typearticle
Languageen
FieldComputer Science
TopicGaussian Processes and Bayesian Inference
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsContinuationArtificial intelligenceGaussianDeep learningComputer sciencePsychologyPhysics

Abstract

fetched live from OpenAlex

In this paper, we develop a Gaussian continuation framework for deep learning, which is an optimization strategy that involves smoothing the loss function by convolving it with a Gaussian kernel. The width of the kernel is decreased over the optimization steps leading to the degree of smoothing being gradually relaxed during training. This enables gradient-based optimization to more easily traverse suboptimal local minima in non-convex loss landscapes. We carefully study the unique theoretical difficulties for continuation posed by deep learning applications, and how classical assumptions made in theoretical analysis of continuation methods must be revised or qualified. Our analysis shows that if the width of the Gaussian kernel is treated as an optimization variable, it naturally tends to zero in virtually all minimization problems. As a consequence, Gaussian continuation will converge to the minima of the original loss function as long as the base optimizer is capable of escaping saddle points. We demonstrate that Gaussian continuation outperforms baseline methods in training a regression network and a convolutional generative adversarial network (GAN).

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.970
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0010.008
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 head0.031
GPT teacher head0.309
Teacher spread0.278 · 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