112 citations · 298 across the 25 of their papers we have counts for
10 papers · 1 filter
Interacting particle guidance for sampling reward-tilted generative priors
Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund +1
Inference-time steering adapts pretrained diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or samples with desired properties…
ESS-Flow: Training-free guidance of flow-based models as inference in source space
Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund +1
Guiding pretrained flow-based generative models for conditional generation or to produce samples with desired target properties enables solving diverse tasks without retraining on…
Learning incomplete factorization preconditioners for GMRES
Paul Häusner, Aleix Nieto Juscafresa, Jens Sjölund
Incomplete LU factorizations of sparse matrices are widely used as preconditioners in Krylov subspace methods to speed up solving linear systems. Unfortunately, computing the preco…
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
Ruoqi Zhang, Ziwei Luo, Jens Sjölund +2
This paper presents advanced techniques of training diffusion policies for offline reinforcement learning (RL). At the core is a mean-reverting stochastic differential equation (SD…
Variational Elliptical Processes
Maria Bånkestad, Jens Sjölund, Jalil Taghia +1
We present elliptical processes, a family of non-parametric probabilistic models that subsume Gaussian processes and Student's t processes. This generalization includes a range of…
On Feynman--Kac training of partial Bayesian neural networks
Zheng Zhao, Sebastian Mair, Thomas B. Schön +1
Recently, partial Bayesian neural networks (pBNNs), which only consider a subset of the parameters to be stochastic, were shown to perform competitively with full Bayesian neural n…
Risk-sensitive Actor-free Policy via Convex Optimization
Ruoqi Zhang, Jens Sjölund
Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-…
Archetypal Analysis++: Rethinking the Initialization Strategy
Sebastian Mair, Jens Sjölund
Archetypal analysis is a matrix factorization method with convexity constraints. Due to local minima, a good initialization is essential, but frequently used initialization methods…
Image Restoration with Mean-Reverting Stochastic Differential Equations
Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao +2
This paper presents a stochastic differential equation (SDE) approach for general-purpose image restoration. The key construction consists in a mean-reverting SDE that transforms a…
Graph-based Neural Acceleration for Nonnegative Matrix Factorization
Jens Sjölund, Maria Bånkestad
We describe a graph-based neural acceleration technique for nonnegative matrix factorization that builds upon a connection between matrices and bipartite graphs that is well-known…