MétaCan
Menu
Back to cohort
Record W2966418478 · doi:10.48550/arxiv.1809.04092

A Fixed-Depth Size-Hierarchy Theorem for AC$^0[\\oplus]$ via the Coin\n Problem

2018· article· en· W2966418478 on OpenAlexaff

Bibliographic record

VenuearXiv (Cornell University) · 2018
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning and Algorithms
Canadian institutionsMemorial University of NewfoundlandSimon Fraser University
Fundersnot available
KeywordsCircuit complexityBoolean circuitMathematicsBoolean functionDiscrete mathematicsTruth tableCombinatoricsBinary logarithmUpper and lower boundsFunction (biology)PolynomialParity functionComputable functionRandom oracleElectronic circuitAlgorithmComputer scienceBoolean expressionPhysicsMathematical analysisQuantum mechanics

Abstract

fetched live from OpenAlex

We prove the first Fixed-depth Size-hierarchy Theorem for uniform\nAC$^0[\\oplus]$ circuits; in particular, for fixed $d$, the class\n$\\mathcal{C}_{d,k}$ of uniform AC$^0[\\oplus]$ formulas of depth $d$ and size\n$n^k$ form an infinite hierarchy. For this, we find the first class of explicit\nfunctions giving (up to polynomial factor) matching upper and lower bounds for\nAC$^0[\\oplus]$ formulas, derived from the $\\delta$-Coin Problem, the\ncomputational problem of distinguishing between coins that are heads with\nprobability $(1+\\delta)/2$ or $(1-\\delta)/2,$ where $\\delta$ is a parameter\ngoing to $0$. We study this problem's complexity and make progress on both\nupper bounds and lower bounds.\n Upper bounds. We find explicit monotone AC$^0$ formulas solving the\n$\\delta$-coin problem, having depth $d$, size $\\exp(O(d(1/\\delta)^{1/(d-1)}))$,\nand sample complexity poly$(1/\\delta)$, for constant $d\\ge2$. This matches\nprevious upper bounds of O'Donnell and Wimmer (ICALP 2007) and Amano (ICALP\n2009) in terms of size and improves the sample complexity.\n Lower bounds. The upper bounds are nearly tight even for the stronger model\nof AC$^0[\\oplus]$ formulas (which allow NOT and Parity gates): any\nAC$^0[\\oplus]$ formula solving the $\\delta$-coin problem must have size\n$\\exp(\\Omega(d(1/\\delta)^{1/(d-1)})).$ This strengthens a result of Cohen,\nGanor and Raz (APPROX-RANDOM 2014), who prove a similar result for AC$^0$, and\na result of Shaltiel and Viola (SICOMP 2010), who give a superpolynomially\nweaker (still exponential) lower bound.\n The upper bound is a derandomization involving a use of Janson's inequality\n(as far as we know, the first such use of the inequality) and classical\ncombinatorial designs. For the lower bound, we prove an optimal (up to constant\nfactor) degree lower bound for multivariate polynomials over $\\mathbb{F}_2$\nsolving the $\\delta$-coin problem, which may be of independent interest.\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.

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)0.001
metaresearch head score (Gemma)0.010
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 score0.016
Threshold uncertainty score0.053

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.010
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0010.001
Science and technology studies0.0010.003
Scholarly communication0.0030.009
Open science0.0020.004
Research integrity0.0010.004
Insufficient payload (model declined to judge)0.0160.001

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 head0.029
GPT teacher head0.191
Teacher spread0.162 · 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

Citations13
Published2018
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicMachine Learning and AlgorithmsFrench-language works237,207