Odds Law: The Decomposition Algebra On How Intelligence Organizes Itself to Solve Difficult Problems Reliably

• URL: http://arxiv.org/abs/2606.15712v1
• Date: Sun, 14 Jun 2026 09:53:11 GMT
• Title: Odds Law: The Decomposition Algebra On How Intelligence Organizes Itself to Solve Difficult Problems Reliably
• Abstract summary: We show that reliability is bought with independent information arranged by composition, and bounded by the verifier.<n>In short, reliability is neither free nor magical: it is bought with independent information, arranged by composition, and bounded by the verifier.
• Score: 0.5414847001704247
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We ask a structural question: given unreliable elementary problem-solvers, what organizations of them solve hard problems reliably, and what are the limits? We develop a $decomposition~algebra$: elementary solvers are morphisms in a stochastic category, and four combinators (sequential composition, parallel ensembling, verification gating, and recursive reduction) generate the space of compound solvers. We equip this algebra with two homomorphisms, a $reliability$ valuation into the ordered monoid $([0,1],\le)$ and a $cost$ valuation into a commutative semiring, and we derive the composition laws that govern how reliability flows through structure. Our central results are (i) a $verification~odds~law$ (the result that names this report), showing that a verification gate multiplies the odds of correctness by the verifier's likelihood ratio $Λ$, so that $k$ conditionally independent gates yield geometric amplification; (ii) a $reliability~amplification~theorem$, giving target reliability $1-δ$ at $O(\log 1/δ)$ verification depth whenever $Λ>1$; and (iii) a $threshold~dichotomy$: above the critical parameters reliability can be driven arbitrarily close to one at logarithmic cost, while at or below them no amplification is possible. We then show that $self-organization$ is the least fixed point of a monotone improvement operator on the complete lattice of strategies, and that this fixed point equalizes marginal log-odds gain per unit cost. Finally, we prove matching limits: an information ceiling bounds per-gate amplification by a divergence quantity; shared error causes create a strictly positive voting floor, so diversity is $necessary$ for unbounded amplification. Reliability, in short, is neither free nor magical: it is bought with independent information, arranged by composition, and bounded by the verifier.

Related papers

• Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification [10.999442451351385]
  We show that the order-oblivious instance-wise lower bound is $ (H(I)[log(1/)+Ent(I)]).<n>We also give a single $$-correct algorithm with expected sample complexity $ O ( H(I)[log(e+log(e+D))),D=_[2]-2, $ without prior knowledge of the gaps.<n>Our lower bound removes the dyadic-gap and monotonicity restrictions of previous work, and our upper bound removes the additional polylogarithmic
  arXiv  Detail & Related papers  (2026-09-12T04:31:38Z)
• Dimension Dependent Correlation Gap Bounds under Restricted Independence [0.0]
  We show that the worst case pairwise independent correlation gap attains $e/(e-1)$ally.<n>Despite being the least restrictive form of independence in the $t$-wise independence hierarchy, pairwise independence can be as restrictive as mutual independence in the worst case.
  arXiv  Detail & Related papers  (2026-09-02T14:33:55Z)
• The geometry of AI validation: Exact certification limits for iid best-of-N search [0.0]
  We represent validation and deployment rules as kernels over a reliability surface.<n>Knowing best-of-$n$ reliability through $n=m$ leaves exact ambiguity width $B_m,N=1+2sum_r=1m(-1)rcos2Nr/[(m+1)]$.
  arXiv  Detail & Related papers  (2026-08-21T15:18:11Z)
• Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability [51.56484100374058]
  We prove the first identifiability theorem for a mechanistic-interpretability primitive.<n>The spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition.
  arXiv  Detail & Related papers  (2026-08-10T19:42:01Z)
• AI-Assisted Discovery of Convex Relaxations via Dual Agents [56.60366723277675]
  We show that a lower bound holds for every admissible function and follows from a convex relaxation giving stronger bounds.<n>A theory verifies each agent one and searches for counterexamples, and every reported bound is certified by an explicit dual-feasible point in the interval.
  arXiv  Detail & Related papers  (2026-06-30T06:10:25Z)
• All you need is log [0.42671348654734564]
  We show that the Rényi divergences of order $in[0,infty]$ are the unique family monotone under data processing and additive on independent products.<n>Many problems compare more than two distributions at once -- multi-population fairness, multi-prior PAC-Bayes bounds, multi-hypothesis testing.<n>The right multi-distribution generalization of the Rényi family has been an open question.
  arXiv  Detail & Related papers  (2026-06-25T17:54:49Z)
• SILAGE: Memory-Efficient, Full-Gradient-Free Nonconvex Optimization for Nested Finite Sums [51.49970814177172]
  Empirical risk on datasets naturally exhibits similarities in $N=nm$ total samples.<n>We provide an analysis that avoids pessimistic convergence analysis.<n>Our results improve existing state-of-the-art regimes.
  arXiv  Detail & Related papers  (2026-06-14T14:11:07Z)
• A Mathematical Theory of Value: a synthesis on goal-directed agency under resource constraints [6.057587531186626]
  We show that value, the quantity goal-directed agents create, destroy, and exchange, is a lawful structural quantity in the same category as information.<n>For populations, value is frame-relative while price is frame-independent; a fleet that pools its resource and fuses its perception inherits the ceiling.
  arXiv  Detail & Related papers  (2026-06-10T16:11:04Z)
• Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale [54.65053906803857]
  We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability.<n>Our main result establishes a scale-sensitive generalization of the fundamental theorem of PAC learning.<n>We also highlight several open questions on quantitative sample complexity and evaluability.
  arXiv  Detail & Related papers  (2026-05-13T15:41:30Z)
• Strategic PAC Learnability via Geometric Definability [69.34283267701421]
  Strategic classification studies learning settings in which individuals can modify their features, at a cost, in order to influence the classifier's decision.<n>A central question is how the sample complexity of the induced (strategic) hypothesis class depends on the complexities of the underlying hypothesis class and the cost structure governing feasible manipulations.<n>We introduce structure via a geometric definability assumption: both the hypothesis class and the cost-induced neighborhood relation can be defined by first-order formulas over $mathbbR_mathttexp$.<n>We prove that learnability is preserved, with sample complexity controlled by the complexity
  arXiv  Detail & Related papers  (2026-05-13T12:21:56Z)
• FlowBoost Reveals Phase Transitions and Spectral Structure in Finite Free Information Inequalities [1.4721615285883427]
  We investigate the finite free Stam for real-rooted inequalitys under finite free additive convolution $boxplus_n$.<n>At $p=2$ FlowBoost finds the Hermite pair as unique the equality case.<n>We conjecture that the values of the doubly coupling matrix $E_n$ on the mean-zero subspace are $2k/2:k=1,ldots,n-1$.
  arXiv  Detail & Related papers  (2026-04-13T18:09:32Z)
• Exact Structural Abstraction and Tractability Limits [0.0]
  Exact correctness depends only on the induced classes $s sim_R simation' iff mathrmAdm_R(s)$.<n>Decision, search, approximation, statistical, randomized horizon, and distributional guarantees all reduce to this same quotient-recovery problem.
  arXiv  Detail & Related papers  (2026-04-08T17:59:47Z)
• Linear Contextual Bandits with Adversarial Corruptions [91.38793800392108]
  We study the linear contextual bandit problem in the presence of adversarial corruption. We present a variance-aware algorithm that is adaptive to the level of adversarial contamination $C$.
  arXiv  Detail & Related papers  (2021-10-25T02:53:24Z)
• Robustly Learning any Clusterable Mixture of Gaussians [55.41573600814391]
  We study the efficient learnability of high-dimensional Gaussian mixtures in the adversarial-robust setting. We provide an algorithm that learns the components of an $epsilon$-corrupted $k$-mixture within information theoretically near-optimal error proofs of $tildeO(epsilon)$. Our main technical contribution is a new robust identifiability proof clusters from a Gaussian mixture, which can be captured by the constant-degree Sum of Squares proof system.
  arXiv  Detail & Related papers  (2020-05-13T16:44:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.