Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
Title resolution pending
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative 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.
A probabilistic extension of the win ratio that uses conditional probabilities of win/loss/tie to handle coarsened data in prioritized composite endpoints while reducing exactly to the classical estimator when data are complete.
Proposes a scale-calibrated median-of-means estimator for robust aggregation of distributed PCA estimates on the product of Euclidean space and Grassmann manifold.
A large deviations principle is established for rogue waves in the cubic nonlinear Schrödinger equation with randomized quasi-periodic initial data in dimensions d>1, holding for times O(ε^{-1-η}) under polynomial Fourier decay.
The paper introduces a noise-state recursive representation for finite-player dynamic games with dispersed private information, yielding explicit equilibrium characterizations in continuous-time LQG settings.
Derives combinatorial expression for degrees of tensor train varieties via integral geometry and releases Julia package TTVarietyDegree.jl.
Generative models for cosmological field-level inference can reproduce posterior means and cross-correlations yet fail to capture correct uncertainty geometry when validated against HMC reference samples.
Centralized matching mechanisms outperform free negotiation in stability and efficiency with LLM agents, who also report preferences truthfully more often than humans, though not always in line with strategy-proofness predictions.
Derives exact operating characteristic corrections and a numerical search over sample sizes to obtain optimal two-stage Bayes factor designs for two-arm binary-endpoint phase II trials that minimize expected sample size under the null.
Proves Poisson property for transformed excursion point processes under state-dependent inverse-subordinator time changes of regenerative processes and derives multiscale joint occupation-time limit theorems including generalized arcsine and Darling-Kac laws under regular variation.
Unified framework for complex zero-sum games with chance constraints that converts probabilistic constraints into convex second-order cone programs under various distribution assumptions.
Prevent-Jack fuses six local behaviors into a context steering framework for swarms of heavy articulated vehicles, delivering collision and jackknifing avoidance at the expense of deadlocks and livelocks observed in 15,000 simulations.
Derives exact distributions for two-step restricted-angle 2D random walks, numerical solutions for general steps, large-step approximations, and exact support characterization.
First evidence for non-zero φ_s in B_s^0 → J/ψ φ decays at 3.2σ from CMS 13 TeV data combined with prior 8 TeV result.
Diffusion models via DDPM work for anomaly detection but are slow; the proposed DTE method estimates diffusion time distribution analytically and with a neural net to deliver faster inference while outperforming DDPM on ADBench for unsupervised and semi-supervised settings.
Deep learning system synthesizes intermediate head CT slices to halve through-plane anisotropy while providing implicit denoising, outperforming baselines on structural metrics.
A multi-objective probabilistic forecast combination framework is introduced that generates Pareto-optimal combinations balancing forecast accuracy and inventory decision performance, outperforming single-objective methods on retail and spare parts data.
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.
A novel MPI-based construction method for spiking neural networks on multi-GPU clusters is introduced, with scaling demonstrated on two cortical models using point-to-point and collective communication.
Thermodynamics emerges as the complete-similarity limit of statistical mechanics when the small-system group Π_B = k_B/(c ℓ³) becomes irrelevant at macroscopic scales.
A review summarizing definitions, canonical forms, exact and approximate distributions, numerical methods, applications, and open problems for quadratic forms in real and complex Gaussian variables, including multiforms and ratios.
citing papers explorer
-
On Diffusion Modeling for Anomaly Detection
Diffusion models via DDPM work for anomaly detection but are slow; the proposed DTE method estimates diffusion time distribution analytically and with a neural net to deliver faster inference while outperforming DDPM on ADBench for unsupervised and semi-supervised settings.