Establishes discrete log-concavity of ground states for convex potentials and extends Reichardt's HWS tunneling analysis to quadratic spikes via new spectral gap bounds.
hub
Rand , title =
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 3 cs.CL 2 math.ST 2 astro-ph.GA 1 cs.AI 1 cs.GT 1 cs.IT 1 econ.GN 1 math.OC 1 quant-ph 1years
2026 16roles
background 2polarities
background 2representative citing papers
Direct fixed-weight solver for free-support Wasserstein medians relocates atoms using OT barycentric projections and inverse-distance weights, achieving monotone descent on smoothed objectives with fewer subproblems than nested Weiszfeld baselines.
Proves that no behavior-dependent feedback training strategy can guarantee an honest agent for latent knowledge even with perfect training feedback.
Soft-MSM is a smooth, gradient-enabled version of the context-aware MSM distance for time series alignment that outperforms Soft-DTW alternatives in clustering and nearest-centroid classification.
Introduces decision-alignment to evaluate uncertainty metrics against downstream decision utilities and proposes prior-weighted proper scoring rules that align better in benchmarks and case studies.
Kling-Gupta linear regression scales the OLS coefficient vector by a variance-inflation factor based on sample moments, preserves response variance on the training set, and converges almost surely to explicit population limits while maximizing KGE but not NSE.
Collision statistics yield finite-resolution approximations to Shannon entropy and mutual information via Rényi entropies, with derived interpolation-error bounds that separate deterministic approximation error from finite-sample estimation error.
A new geographically weighted penalized compositional regression model with pairwise fusion penalty is proposed to handle spatial heterogeneity and compositional covariates, demonstrated on U.S. income and COPD data.
Non-affine approval functions create unavoidable miscalibration in proper scoring rules for strategic agents, but step-function thresholds enable first-best screening without it, uniquely for the Brier score.
Machine translation preserves embedding similarity structure for ten languages but distorts it for four in the Manifesto Corpus, via a new non-inferiority testing framework.
A review reframing density estimation as 'density evolution' across scales, linking kernel smoothing to heat flow, mixtures to compression, and topology to level sets, while stating three structural results on modes, Gaussian semigroups, and log-concavity.
The Stakeholder Grounding Exercise shows neural text embeddings are 19-26pp less reliable than human experts at capturing semantic distinctions, with misalignment strongly correlated to poorer clustering performance (ρ=0.9), replicated across Danish policy and US AI domains.
A nonmonotone subgradient algorithm is developed for upper-C^2 optimization on submanifolds with stationarity and KL-based convergence guarantees.
MtFAD plus MOBSynC on GAMA data yields eight simple clusters that merge into red and blue sequences containing substructure tied to mass quenching, environmental quenching, morphology and environment.
Economics shows declining overall self-referentiality after 2008 but persistent high closure in CORE and Finance clusters, with CORE acting as a net knowledge exporter in a hierarchical journal system.
citing papers explorer
-
The Impossibility of Eliciting Latent Knowledge
Proves that no behavior-dependent feedback training strategy can guarantee an honest agent for latent knowledge even with perfect training feedback.