Zobrazeno 1 - 10
of 818
pro vyhledávání: '"Schön, Thomas"'
Given an unconditional diffusion model $\pi(x, y)$, using it to perform conditional simulation $\pi(x \mid y)$ is still largely an open question and is typically achieved by learning conditional drifts to the denoising SDE after the fact. In this wor
Externí odkaz:
http://arxiv.org/abs/2405.13794
Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets. Typically, diffusion models trained in specific datasets fail to recover images that ha
Externí odkaz:
http://arxiv.org/abs/2404.09732
Recently, several direct Data-Driven Predictive Control (DDPC) methods have been proposed, advocating the possibility of designing predictive controllers from historical input-output trajectories without the need to identify a model. In this work, we
Externí odkaz:
http://arxiv.org/abs/2403.05860
This paper presents advanced techniques of training diffusion policies for offline reinforcement learning (RL). At the core is a mean-reverting stochastic differential equation (SDE) that transfers a complex action distribution into a standard Gaussi
Externí odkaz:
http://arxiv.org/abs/2402.04080
Autor:
Baumann, Dominik, Schön, Thomas B.
When deploying machine learning algorithms in the real world, guaranteeing safety is an essential asset. Existing safe learning approaches typically consider continuous variables, i.e., regression tasks. However, in practice, robotic systems are also
Externí odkaz:
http://arxiv.org/abs/2401.05876
The goal of this paper is to provide a system identification-friendly introduction to the Structured State-space Models (SSMs). These models have become recently popular in the machine learning community since, owing to their parallelizability, they
Externí odkaz:
http://arxiv.org/abs/2312.06211
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 networks. However, pBNNs are often multi-modal in the latent variable s
Externí odkaz:
http://arxiv.org/abs/2310.19608
Autor:
Baumann, Dominik, Noorani, Erfaun, Price, James, Peters, Ole, Connaughton, Colm, Schön, Thomas B.
Envisioned application areas for reinforcement learning (RL) include autonomous driving, precision agriculture, and finance, which all require RL agents to make decisions in the real world. A significant challenge hindering the adoption of RL methods
Externí odkaz:
http://arxiv.org/abs/2310.11335
State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against it. Formulated as a min-max problem, it searches for the
Externí odkaz:
http://arxiv.org/abs/2310.10807
Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates dramatically due to c
Externí odkaz:
http://arxiv.org/abs/2310.01018