5 papers
Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences
Viktor Stein, Adwait Datar, Nihat Ay
Kullback-Leibler (KL) divergence regularization is widely used in reinforcement learning, but it becomes infinite under support mismatch and can degenerate in low-noise regimes. Us…
Approximating -Divergences with Rank Statistics
Viktor Stein, José Manuel de Frutos
We introduce a rank-statistic approximation of -divergences that avoids explicit density-ratio estimation by working directly with the distribution of ranks. For a resolution pa…
Biological Engineering: What does it mean? Where does it (need to) go?
Ulrike A. Nuber, Viktor Stein
Biological engineering, the convergence between engineering and biology, is at the forefront of significant advances in healthcare, agriculture, and environmental sustainability, m…
Towards understanding Accelerated Stein Variational Gradient Flow -- Analysis of Generalized Bilinear Kernels for Gaussian target distributions
Viktor Stein, Wuchen Li
Stein variational gradient descent (SVGD) is a kernel-based and non-parametric particle method for sampling from a target distribution, such as in Bayesian inference and other mach…
Accelerated Stein Variational Gradient Flow
Viktor Stein, Wuchen Li
Stein variational gradient descent (SVGD) is a kernel-based particle method for sampling from a target distribution, e.g., in generative modeling and Bayesian inference. SVGD does…