Zobrazeno 1 - 10
of 94
pro vyhledávání: '"Trapp, Martin"'
Publikováno v:
In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), 2024
A probabilistic circuit (PC) succinctly expresses a function that represents a multivariate probability distribution and, given sufficient structural properties of the circuit, supports efficient probabilistic inference. Typically a PC computes the p
Externí odkaz:
http://arxiv.org/abs/2408.04229
Autor:
Yao, Lingyun, Trapp, Martin, Leslin, Jelin, Singh, Gaurav, Zhang, Peng, Periasamy, Karthekeyan, Andraud, Martin
Probabilistic circuits (PCs) offer a promising avenue to perform embedded reasoning under uncertainty. They support efficient and exact computation of various probabilistic inference tasks by design. Hence, hardware-efficient computation of PCs is hi
Externí odkaz:
http://arxiv.org/abs/2405.13639
Deployment of deep neural networks in real-world settings typically requires adaptation to new tasks with few examples. Few-shot classification (FSC) provides a solution to this problem by leveraging pre-trained backbones for fast adaptation to new c
Externí odkaz:
http://arxiv.org/abs/2404.07696
In many real-world scenarios, it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data. Probabilistic circuits (PCs), a prominent family of tractable probabilistic models, offer a rem
Externí odkaz:
http://arxiv.org/abs/2312.07790
Autor:
Loconte, Lorenzo, Sladek, Aleksanteri M., Mengel, Stefan, Trapp, Martin, Solin, Arno, Gillis, Nicolas, Vergari, Antonio
Mixture models are traditionally represented and learned by adding several distributions as components. Allowing mixtures to subtract probability mass or density can drastically reduce the number of components needed to model complex distributions. H
Externí odkaz:
http://arxiv.org/abs/2310.00724
Autor:
Yu, Xuanlong, Zuo, Yi, Wang, Zitao, Zhang, Xiaowen, Zhao, Jiaxuan, Yang, Yuting, Jiao, Licheng, Peng, Rui, Wang, Xinyi, Zhang, Junpei, Zhang, Kexin, Liu, Fang, Alcover-Couso, Roberto, SanMiguel, Juan C., Escudero-Viñolo, Marcos, Tian, Hanlin, Matsui, Kenta, Wang, Tianhao, Adan, Fahmy, Gao, Zhitong, He, Xuming, Bouniot, Quentin, Moghaddam, Hossein, Rai, Shyam Nandan, Cermelli, Fabio, Masone, Carlo, Pilzer, Andrea, Ricci, Elisa, Bursuc, Andrei, Solin, Arno, Trapp, Martin, Li, Rui, Yao, Angela, Chen, Wenlong, Simpson, Ivor, Campbell, Neill D. F., Franchi, Gianni
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural advers
Externí odkaz:
http://arxiv.org/abs/2309.15478
Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs. In this way, the model can adjust to a limi
Externí odkaz:
http://arxiv.org/abs/2302.06359
The dynamic Schr\"odinger bridge problem provides an appealing setting for solving constrained time-series data generation tasks posed as optimal transport problems. It consists of learning non-linear diffusion processes using efficient iterative sol
Externí odkaz:
http://arxiv.org/abs/2301.13636