Zobrazeno 1 - 10
of 3 287
pro vyhledávání: '"P. Ziemann"'
Diffusion-based generative models provide a powerful framework for learning to sample from a complex target distribution. The remarkable empirical success of these models applied to high-dimensional signals, including images and video, stands in star
Externí odkaz:
http://arxiv.org/abs/2410.11275
A driving force behind the diverse applicability of modern machine learning is the ability to extract meaningful features across many sources. However, many practical domains involve data that are non-identically distributed across sources, and stati
Externí odkaz:
http://arxiv.org/abs/2410.11227
Research on transcranial magnetic stimulation (TMS) combined with encephalography feedback (EEG-TMS) has shown that the phase of the sensorimotor mu rhythm is predictive of corticospinal excitability. Thus, if the subject-specific optimal phase is kn
Externí odkaz:
http://arxiv.org/abs/2410.05747
How many parameters are required for a model to execute a given task? It has been argued that large language models, pre-trained via self-supervised learning, exhibit emergent capabilities such as multi-step reasoning as their number of parameters re
Externí odkaz:
http://arxiv.org/abs/2409.13421
Autor:
Ziemann, Ingvar
In this note, we give a short information-theoretic proof of the consistency of the Gaussian maximum likelihood estimator in linear auto-regressive models. Our proof yields nearly optimal non-asymptotic rates for parameter recovery and works without
Externí odkaz:
http://arxiv.org/abs/2409.06437
Autor:
Ziemann, Volker
Even though many of the experiments leading to the standard model of particle physics were done at large accelerator laboratories in the US and at CERN, many exciting developments happened in smaller national facilities all over the world. In this re
Externí odkaz:
http://arxiv.org/abs/2405.03430
While subspace identification methods (SIMs) are appealing due to their simple parameterization for MIMO systems and robust numerical realizations, a comprehensive statistical analysis of SIMs remains an open problem, especially in the non-asymptotic
Externí odkaz:
http://arxiv.org/abs/2404.17331
Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a dataset, uses th
Externí odkaz:
http://arxiv.org/abs/2404.09030
We study the quadratic prediction error method -- i.e., nonlinear least squares -- for a class of time-varying parametric predictor models satisfying a certain identifiability condition. While this method is known to asymptotically achieve the optima
Externí odkaz:
http://arxiv.org/abs/2404.07937
Autor:
Ziemann, Volker
Even though many of the experiments leading to the standard model of particle physics were done at large accelerator laboratories in the US and at CERN[1] many exciting developments happened in smaller national facilities all over the world. In this
Externí odkaz:
http://arxiv.org/abs/2404.07088