Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Peluchetti, Stefano"'
Autor:
Peluchetti, Stefano
A Schr\"{o}dinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport problem. We consider the setting where samples from the target dist
Externí odkaz:
http://arxiv.org/abs/2409.09376
Bayesian Neural Networks represent a fascinating confluence of deep learning and probabilistic reasoning, offering a compelling framework for understanding uncertainty in complex predictive models. In this paper, we investigate the use of the precond
Externí odkaz:
http://arxiv.org/abs/2408.14325
Autor:
Peluchetti, Stefano
The scope of this paper is generative modeling through diffusion processes. An approach falling within this paradigm is the work of Song et al. (2021), which relies on a time-reversal argument to construct a diffusion process targeting the desired da
Externí odkaz:
http://arxiv.org/abs/2312.14589
Autor:
Peluchetti, Stefano
Publikováno v:
Journal of Machine Learning Research 24(374):1-51, 2023
The dynamic Schr\"odinger bridge problem seeks a stochastic process that defines a transport between two target probability measures, while optimally satisfying the criteria of being closest, in terms of Kullback-Leibler divergence, to a reference pr
Externí odkaz:
http://arxiv.org/abs/2304.00917
There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions. Two popular problems are: i) the study of the large-width distributio
Externí odkaz:
http://arxiv.org/abs/2206.08065
In modern deep learning, there is a recent and growing literature on the interplay between large-width asymptotic properties of deep Gaussian neural networks (NNs), i.e. deep NNs with Gaussian-distributed weights, and Gaussian stochastic processes (S
Externí odkaz:
http://arxiv.org/abs/2108.02316
Autor:
Massaroli, Stefano, Poli, Michael, Peluchetti, Stefano, Park, Jinkyoo, Yamashita, Atsushi, Asama, Hajime
Publikováno v:
IEEE Control Systems Letters, 2021
We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of adjoint sensitivity results for stochastic differential equations thro
Externí odkaz:
http://arxiv.org/abs/2106.03780
In this paper, we consider fully connected feed-forward deep neural networks where weights and biases are independent and identically distributed according to Gaussian distributions. Extending previous results (Matthews et al., 2018a;b; Yang, 2019) w
Externí odkaz:
http://arxiv.org/abs/2102.10307
The count-min sketch (CMS) is a time and memory efficient randomized data structure that provides estimates of tokens' frequencies in a data stream of tokens, i.e. point queries, based on random hashed data. A learning-augmented version of the CMS, r
Externí odkaz:
http://arxiv.org/abs/2102.04462
The count-min sketch (CMS) is a randomized data structure that provides estimates of tokens' frequencies in a large data stream using a compressed representation of the data by random hashing. In this paper, we rely on a recent Bayesian nonparametric
Externí odkaz:
http://arxiv.org/abs/2102.03743