Pith. sign in

REVIEW 11 cited by

Generic and lifted probabilistic comparisons -- max replaces minmax

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1612.08506 v1 pith:47524GHX submitted 2016-12-27 math.PR cs.ITmath.ITmath.STstat.TH

classification math.PRcs.ITmath.ITmath.STstat.TH
keywords comparisonresultsminmaxprinciplecollectionconceptgeneralhere
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper we introduce a collection of powerful statistical comparison results. We first present the results that we obtained while developing a general comparison concept. After that we introduce a separate lifting procedure that is a comparison concept on its own. We then show how in certain scenarios the lifting procedure basically represents a substantial upgrade over the general strategy. We complement the introduced results with a fairly large collection of numerical experiments that are in an overwhelming agreement with what the theory predicts. We also show how many well known comparison results (e.g. Slepian's max and Gordon's minmax principle) can be obtained as special cases. Moreover, it turns out that the minmax principle can be viewed as a single max principle as well. The range of applications is enormous. It starts with revisiting many of the results we created in recent years in various mathematical fields and recognizing that they are fully self-contained as their starting blocks are specialized variants of the concepts introduced here. Further upgrades relate to core comparison extensions on the one side and more practically oriented modifications on the other. Those that we deem the most important we discuss in several separate companion papers to ensure preserving the introductory elegance and simplicity of what is presented here.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Precise sample covariance spectral norm error -- an RDT view

    math.ST 2026-07 conditional novelty 6.0 of 10

    For Gaussian data in the proportional limit, the spectral-norm error of the sample covariance converges to γ̂√φ1/(√φ1−√α), with γ̂ solving an equation in the covariance spectrum.

  2. An RDT based approach to large deviations of Wishart and Wigner matrices spectral edges

    math.PR 2026-06 unverdicted novelty 6.0 of 10

    Develops an RDT-based LDP framework for spectral edges of Wishart and Wigner matrices matching prior Coulomb gas results.

  3. Ground state energies of multipartite $p$-spin models -- partially lifted RDT view

    math.PR 2025-09 conditional novelty 6.0 of 10

    The paper uses partially lifted random duality theory to derive matching ground-state-energy bounds for spherical multipartite pure p-spin models and proves the Subag and Dartois-McKenna formulas agree exactly.

  4. Optimal spectral initializers impact on phase retrieval phase transitions -- an RDT view

    stat.ML 2025-06 conditional novelty 6.0 of 10

    Optimal spectral initializers at the theoretical phase retrieval threshold sit in flat landscape regions, so roughly 15% oversampling is needed for reliable descending algorithms.

  5. Phase transition of \emph{descending} phase retrieval algorithms

    stat.ML 2025-06 reject novelty 6.0 of 10

    The paper derives RDT-based lower bounds and predicts a phase transition at oversampling ratio α≈1.4 where descending phase retrieval algorithms transition from failing to succeeding, but the key isomorphism with conv...

  6. Deep ReLU networks -- injectivity capacity upper bounds

    stat.ML 2024-12 reject novelty 6.0 of 10

    For deep ReLU networks with random Gaussian weights, the paper gives upper bounds on the layer expansion needed for injectivity and finds the expansion need saturates by four layers.

  7. A CLuP algorithm to practically achieve $\sim 0.76$ SK--model ground state free energy

    cond-mat.dis-nn 2025-07 conditional novelty 5.0 of 10

    The authors propose a CLuP-SK barrier-descent algorithm and report it achieves approximately 0.76 of the SK ground state free energy for n around 2000 to 8000, approaching the theoretical Parisi limit of about 0.763.

  8. Fully lifted \emph{blirp} interpolation -- a large deviation view

    math.PR 2025-06 conditional novelty 5.0 of 10

    A large-deviation upgrade of fully lifted blirp interpolation is derived, yielding explicit derivative identities that the author links to local entropy and computational gaps in perceptron models.

  9. Phase retrieval with rank $d$ measurements -- \emph{descending} algorithms phase transitions

    stat.ML 2025-06 conditional novelty 5.0 of 10

    For rank d phase retrieval with Gaussian measurements, descending gradient algorithms are predicted to succeed above a sample complexity ratio near 2.79 for d=2, with lifted bounds lowering this estimate and simulatio...

  10. An RDT based confirmation of Lehner's formula for Kronecker-Gaussian matrices

    math.PR 2026-07 conditional novelty 4.0 of 10

    This paper uses Random Duality Theory to give an alternative proof of Lehner's deterministic spectral edge formula for Kronecker-Gaussian matrices.

  11. A large deviation view of \emph{stationarized} fully lifted blirp interpolation

    math.PR 2025-06 conditional novelty 4.0 of 10

    The paper derives new derivative identities for a stationarized fully lifted bilinearly indexed random process interpolator and states an equality between large deviation limits at the opposite ends of an interpolation path.

Pith tools