The result sharply distinguishes between local stochastic fluctuation and global sample complexity in distributional RL, with the deterministic transient and burn-in depending on the smallest Bellman-target density (order m^(-1) in worst case).
Synchronous quantile temporal-difference learning (QTD) in tabular distributional reinforcement learning has a global finite-sample guarantee with leading last-iterate fluctuation of order Õ(T^(-a/2)/√(1-γ)) for stepsizes α_t=c(t+1)^(-a) with a∈(1/2,1), with no polynomial dependence on the number of quantiles.
TRACE-CRC avoids the trajectory undercoverage problems of compact stepwise and adaptive conformal baselines
Adaptive domain augmentation for inverse problems can be given a principled Bayesian justification that ensures robust inference under incomplete prior knowledge
Active diffusion-based methods can discover correct parameter regions even when initial training bounds exclude true parameters by iteratively detecting and correcting model misspecification through posterior uncertainty
The proposed diffusion-based inverse solver is effective for quantum chromodynamics analysis of nucleon structure, specifically parameterizing quantum correlation functions to event observables
TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections
Diffusion models can be trained to learn the mapping between parameter space and observable space for solving inverse problems
Modern deep learning-based CSI predictors often provide only point predictions and lack calibrated uncertainty estimates
Column-permutation parallel analysis violates function-preserving reparameterization invariance because its reference distribution and component count can change while the model function remains fixed
Permutation-equivariant architectures are motivated by the fact that graphs are invariant under node permutations
Quotient couplings can be lifted to aligned representatives without additional cost
Hidden coordinates in language models are not uniquely determined by the input-output function, making representation measurements non-invariant to function-preserving basis changes
Causal models learn more generalizable representations than models trained on observational data alone
The natural Wasserstein geometry for graph pairs compared up to node relabeling is that of the graph quotient space
Data-internal reference procedures face fundamental limitations: they cannot simultaneously preserve coordinate marginals, remain orthogonally equivariant, and remove cross-coordinate covariance
Numerical experiments demonstrate stable support recovery and favorable estimation performance under strong predictor dependence and model-class uncertainty
Current search methods have a weakness in resampling particles at fixed temperature that ignores reward distribution across denoising steps
Discrete diffusion models have become a strong, widely adopted class of generators for sequence data