MétaCan
Menu
Back to cohort
Record W2790987616 · doi:10.1002/nla.2202

Nonlinearly preconditioned L‐BFGS as an acceleration mechanism for alternating least squares with application to tensor decomposition

2018· preprint· en· W2790987616 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

VenueNumerical Linear Algebra with Applications · 2018
Typepreprint
Languageen
FieldMathematics
TopicTensor decomposition and applications
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsBroyden–Fletcher–Goldfarb–Shanno algorithmNonlinear systemTensor (intrinsic definition)AccelerationNonlinear conjugate gradient methodRobustness (evolution)MathematicsConjugate gradient methodQuasi-Newton methodApplied mathematicsMathematical optimizationComputer scienceNewton's methodGeometryGradient descentPhysicsArtificial intelligence

Abstract

fetched live from OpenAlex

Summary We derive nonlinear acceleration methods based on the limited‐memory Broyden–Fletcher–Goldfarb–Shanno (L‐BFGS) update formula for accelerating iterative optimization methods of alternating least squares (ALS) type applied to canonical polyadic and Tucker tensor decompositions. Our approach starts from linear preconditioning ideas that use linear transformations encoded by matrix multiplications and extends these ideas to the case of genuinely nonlinear preconditioning, where the preconditioning operation involves fully nonlinear transformations. As such, the ALS‐type iterations are used as fully nonlinear preconditioners for L‐BFGS, or equivalently, L‐BFGS is used as a nonlinear accelerator for ALS. Numerical results show that the resulting methods perform much better than either stand‐alone L‐BFGS or stand‐alone ALS, offering substantial improvements in terms of time to solution and robustness over state‐of‐the‐art methods for large and noisy tensor problems, including previously described acceleration methods based on nonlinear conjugate gradients and the nonlinear generalized minimal residual method. Our approach provides a general L‐BFGS‐based acceleration mechanism for nonlinear optimization.

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: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.347
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
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 head0.030
GPT teacher head0.355
Teacher spread0.325 · 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