MétaCan
Menu
Back to cohort
Record W2963859684 · doi:10.4230/lipics.itcs.2018.22

Convergence Results for Neural Networks via Electrodynamics

2018· article· en· W2963859684 on OpenAlexaff
Rina Panigrahy‎, Ali Rahimi, Sushant Sachdeva, Qiuyi Zhang

Bibliographic record

VenueDROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2018
Typearticle
Languageen
FieldComputer Science
TopicNeural Networks and Applications
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsGradient descentElectronConvergence (economics)Node (physics)Artificial neural networkPhysicsFunction (biology)Equivalence (formal languages)Descent (aeronautics)MathematicsTopology (electrical circuits)Computer scienceMathematical analysisQuantum mechanicsCombinatoricsDiscrete mathematicsArtificial intelligence

Abstract

fetched live from OpenAlex

We study whether a depth two neural network can learn another 
\ndepth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradient descent converges to the target function is equivalent to the following question in electrodynamics: Given k fixed protons in R^d, and k electrons, each moving due to the attractive force from the protons and repulsive force from the remaining electrons, whether at equilibrium all the electrons will be matched up with the protons, up to a permutation. Under the standard electrical force, this follows from the classic Earnshaw's theorem. In our setting,
\nthe force is determined by the activation function and the
\ninput distribution. Building on this equivalence, we prove the
\nexistence of an activation function such that gradient descent learns at least one of the hidden nodes in the target network. 
\nIterating, we show that gradient descent can be used to learn the entire network one node at a time.

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 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: Methods · Consensus signal: none
Teacher disagreement score0.925
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
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0020.000
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 head0.011
GPT teacher head0.254
Teacher spread0.243 · 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 teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

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

Citations13
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueDROPS (Schloss Dagstuhl – Leibniz Center for Informatics)Same topicNeural Networks and ApplicationsFrench-language works237,207