MétaCan
Menu
Back to cohort
Record W2963201904

Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds

2018· article· en· W2963201904 on OpenAlexaff
Kry Yik Chau Lui, Gavin Weiguang Ding, Ruitong Huang, Robert J. McCann

Bibliographic record

VenueNeural Information Processing Systems · 2018
Typearticle
Languageen
FieldComputer Science
TopicTopological and Geometric Data Analysis
Canadian institutionsUniversity of TorontoUniversity of Alberta
Fundersnot available
KeywordsMeasure (data warehouse)Dimensionality reductionMathematical proofComputer scienceReduction (mathematics)Lipschitz continuityKey (lock)Curse of dimensionalityAlgorithmMathematicsMathematical optimizationPoint (geometry)Set (abstract data type)Topology (electrical circuits)Data miningArtificial intelligenceCombinatorics
DOInot available

Abstract

fetched live from OpenAlex

In this paper, we investigate Dimensionality reduction (DR) maps in an information retrieval setting from a quantitative topology point of view. In particular, we show that no DR maps can achieve perfect precision and perfect recall simultaneously. Thus a continuous DR map must have imperfect precision. We further prove an upper bound on the precision of Lipschitz continuous DR maps. While precision is a natural measure in an information retrieval setting, it does not measure `how' wrong the retrieved data is. We therefore propose a new measure based on Wasserstein distance that comes with similar theoretical guarantee. A key technical step in our proofs is a particular optimization problem of the $L_2$-Wasserstein distance over a constrained set of distributions. We provide a complete solution to this optimization problem, which can be of independent interest on the technical side.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.126
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.019
Threshold uncertainty score0.100

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.126
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0040.004
Science and technology studies0.0020.014
Scholarly communication0.0080.026
Open science0.0040.013
Research integrity0.0040.010
Insufficient payload (model declined to judge)0.0040.001

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 head0.041
GPT teacher head0.286
Teacher spread0.245 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueNeural Information Processing SystemsSame topicTopological and Geometric Data AnalysisFrench-language works237,207