MétaCan
Menu
Back to cohort
Record W4327873639 · doi:10.48550/arxiv.2110.12217

Deep Structured Teams in Arbitrary-Size Linear Networks: Decentralized\n Estimation, Optimal Control and Separation Principle

2021· preprint· en· W4327873639 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

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicDistributed Control Multi-Agent Systems
Canadian institutionsConcordia University
Fundersnot available
KeywordsKalman filterCurse of dimensionalityMathematical optimizationMathematicsComputer scienceOptimal controlSeparation principleLinear systemDeep learningControl theory (sociology)Nonlinear systemArtificial intelligenceControl (management)

Abstract

fetched live from OpenAlex

In this article, we introduce decentralized Kalman filters for linear\nquadratic deep structured teams. The agents in deep structured teams are\ncoupled in dynamics, costs and measurements through a set of linear regressions\nof the states and actions (also called deep states and deep actions). The\ninformation structure is decentralized, where every agent observes a noisy\nmeasurement of its local state and the global deep state. Since the number of\nagents is often very large in deep structured teams, any naive approach to\nfinding an optimal Kalman filter suffers from the curse of dimensionality.\nMoreover, due to the decentralized nature of information structure, the\nresultant optimization problem is non-convex, in general, where non-linear\nstrategies can outperform linear ones. However, we prove that the optimal\nstrategy is linear in the local state estimate as well as the deep state\nestimate and can be efficiently computed by two scale-free Riccati equations\nand Kalman filters. We propose a bi-level orthogonal approach across both space\nand time levels based on a gauge transformation technique to achieve the above\nresult.\n We also establish a separation principle between optimal control and optimal\nestimation. Furthermore, we show that as the number of agents goes to infinity,\nthe Kalman gain associated with the deep state estimate converges to zero at a\nrate inversely proportional to the number of agents. This leads to a fully\ndecentralized approximate strategy where every agent predicts the deep state by\nits conditional and unconditional expected value, also known as the certainty\nequivalence approximation and (weighted) mean-field approximation,\nrespectively.\n

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: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.728
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.001
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 head0.020
GPT teacher head0.208
Teacher spread0.188 · 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