arXiv:2511.01154v2 Announce Type: replace-cross
Abstract: In this short note, we characterize stability of the Kim–Milman flow map — also known as the probability flow ODE — with respect to variations in the target measure in relative Fisher inform…
arXiv:2604.03015v1 Announce Type: new
Abstract: Given $n$ independent samples from a $d$-dimensional probability distribution, our aim is to generate diffusion-based samples from a distribution obtained by tilting the original, where the degree of til…
arXiv:2505.07647v2 Announce Type: replace-cross
Abstract: We introduce a novel approximation to the same marginal Schr\”{o}dinger bridge using the Langevin diffusion. As $\varepsilon \downarrow 0$, it is known that the barycentric projection (also kno…
arXiv:2604.03218v1 Announce Type: cross
Abstract: Suppose we observe data from a distribution $P$ and we wish to test the composite null hypothesis that $P\in\mathscr P$ against a composite alternative $P\in \mathscr Q\subseteq \mathscr P^c$. Herbert …
arXiv:2310.19603v5 Announce Type: replace
Abstract: The use of attention-based deep learning models in stochastic filtering, e.g. transformers and deep Kalman filters, has recently come into focus; however, the potential for these models to solve stoc…
arXiv:2604.01406v1 Announce Type: cross
Abstract: We study the problem of identifying an optimal coupling between input-output distributional data generated by a causal dynamical system. The coupling is required to satisfy prescribed marginal distribu…
arXiv:2604.01978v1 Announce Type: cross
Abstract: We study a random model of deep multi-head self-attention in which the weights are resampled independently across layers and heads, as at initialization of training. Viewing depth as a time variable, t…
arXiv:2507.18021v2 Announce Type: replace-cross
Abstract: We study the zeroth-order query complexity of sampling from a general logconcave distribution: given access to an evaluation oracle for a convex function $V:\mathbb{R}^{d}\rightarrow\mathbb{R}\…
arXiv:2604.02150v1 Announce Type: cross
Abstract: Samplets are data adapted multiresolution analyses of localized discrete signed measures. They can be constructed on scattered data sites in arbitrary dimension and such that they exhibit vanishing mom…
arXiv:2603.26692v2 Announce Type: replace-cross
Abstract: We introduce a new notion, that of a contextuality profile of a system of random variables. Rather than characterizing a system’s contextuality by a single number, its overall degree of context…