arXiv:2610.35311v1 Announce Type: new Abstract: We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system an...
arXiv:2608. 10896v1 Announce Type: cross Abstract: Constant-stepsize temporal-difference (TD) learning is attractive for policy evaluation, but inference from a single Markov trajectory must account for serial dependence and a stepsize-dependent stationary target.
arXiv:2609.33543v2 Announce Type: replace Abstract: Coupled rollouts can reduce the noise of counterfactual action comparisons, but two issues prevent standard common-random-number constructions from...
arXiv:2606. 16923v1 Announce Type: new Abstract: Simulation-based inference (SBI) of latent parameters is often hindered by simulator misspecification, the mismatch between simulated and real-world observations caused by inherent modeling simplifications.
The paper introduces a theoretical framework to study how perturbations introduced during diffusion model sampling affect the generated output. It defines a path cost based on the Kullback–Leibler divergence between perturbed and reference trajectories, showing that this cost bounds but does not fully determine output changes. Using a response identity, the authors link local perturbation propagation to changes in feature means, revealing that first‑order responses can miss significant output variations. Experiments on pretrained diffusion models demonstrate varying output sensitivity across sampling stages and spatial frequencies, and the framework successfully identifies problematic sampling intervals in cache‑based acceleration.
arXiv:2606. 18186v1 Announce Type: cross Abstract: Finite-dimensional (FD) diffusion policies exhibit temporal drift owing to discretization artifacts that degrade long-horizon performance (when deployed on physical systems).
The paper investigates how perturbations introduced during the sampling process of diffusion models influence the final generated output. It introduces a theoretical framework that quantifies perturbation strength via the Kullback–Leibler divergence, called path cost, and shows that this metric bounds but does not fully determine output changes. Using this framework, the authors derive a response identity linking local perturbations to feature mean changes, and validate their theory through experiments on pretrained diffusion models and cache‑based acceleration techniques.
Diffusion and flow-matching samplers integrate a learned probability-flow ODE from a large noise scale down to a small terminal floor $σ_{\min}$, at which the score is stiff and the flow develops a boundary layer. We treat $σ_{\min}$ as a singular-perturbation parameter and determine which fixed-step samplers are asymptotic-preserving (AP), that is, stable and uniformly accurate as $σ_{\min}\to0$, casting the criteria as an a posteriori audit: residual functionals with $σ_{\min}$-uniform coefficients, computable on a pretrained checkpoint without ground-truth scores or exact trajectories.
arXiv:2607. 12928v1 Announce Type: new Abstract: We study the online binary sequential calibration problem.
arXiv:2606. 05967v1 Announce Type: cross Abstract: In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA).
arXiv:2601. 07094v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) iteratively fits a Gaussian process (GP) surrogate to accumulated evaluations and selects new queries via an acquisition function.
The paper investigates how to collect data for recalibrating a misspecified simulator that models a partially observed real-world system as a fully observed Markovian process. It compares four data‑collection strategies: never recalibrating, passive on‑policy recalibration, continuous exploration across all units, and randomized experimentation on a sample of units. Theoretical analysis and a vending‑machine simulation show that experimentation can outperform passive adaptation when drift is invisible to on‑policy data or when recalibration lags behind ongoing drift, while exploration is preferable when trying worse actions is costly and dynamics may not have changed.