Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal density. However, this choice of latent density can impose unnecessary complexity on the learned flow transformation due to the topological mismatch between the latent and data densities, leading to slower training and suboptimal performance.
arXiv:2606. 29724v1 Announce Type: new Abstract: Normalizing flows are powerful generative models that learn an invertible mapping between complex data distributions and simple latent distributions, typically a standard normal density.
By Liam A. Kruse, Houjun Liu, Alexandros E. Tzikas, Mansur M. Arief, Mykel J. Kochenderfer
arXiv:2607. 19498v1 Announce Type: cross Abstract: Gaussian process (GP) modeling is widely used in computational science and engineering.
By Eric Herrison Gyamfi, Emily L. Kang, Bledar A. Konomi, Guang Lin
arXiv:2604. 13230v2 Announce Type: replace Abstract: Exploratory Landscape Analysis (ELA) provides numerical features for characterizing black-box optimization problems.
By Iv\'an Olarte Rodr\'iguez, Anja Jankovic, Thomas B\"ack, Elena Raponi
arXiv:2410. 10137v5 Announce Type: replace Abstract: We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds.
By Andrew Gracyk
arXiv:2606. 04176v1 Announce Type: new Abstract: We study a distributional generalization of the matrix completion problem in which each entry of the target matrix is a probability distribution rather than a scalar.
By Jiayi Wang, Raymond K. W. Wong
arXiv:2510. 01878v2 Announce Type: replace Abstract: Low-rank gradient optimization for large language models is currently divided into two categories: structured methods that rigorously identify subspaces, and randomized approaches employed primarily for computational efficiency.
By Sahar Rajabi, Nayeema Nonta, Sirisha Rambhatla
arXiv:2510. 02308v2 Announce Type: replace Abstract: Estimating the tangent spaces of a data manifold is a fundamental problem in geometric data analysis.
By Dhruv Kohli, Sawyer J. Robertson, Gal Mishne, Alexander Cloninger
Point cloud denoising is essentially a geometric recovery task that aims to reconstruct the intrinsic structure of a smooth 2D Riemannian manifold embedded in R^3 from noisy, discrete ambient-space samples. Despite the remarkable progress of modern manifold-aware encoders and generative transport models in geometric representation learning, a fundamental objective-geometry mismatch remains underexplored.
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
By Anirban Samaddar, Yixuan Sun, Viktor Nilsson, Sandeep Madireddy
arXiv:2606. 06576v1 Announce Type: new Abstract: In the sciences, regression tasks often require predicting high-dimensional outputs from few training examples.
By Edward T. Stevenson, Eric T. Wolf, Mei Ting Mak, N. J. Mayne, Miles Cranmer
arXiv:2605. 25811v2 Announce Type: replace-cross Abstract: We study counterfactual distribution learning for high-dimensional outcomes whose laws may concentrate near lower-dimensional structure.
By Kwangho Kim