Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Sorrenson, Peter"'
Density-based distances (DBDs) offer an elegant solution to the problem of metric learning. By defining a Riemannian metric which increases with decreasing probability density, shortest paths naturally follow the data manifold and points are clustere
Externí odkaz:
http://arxiv.org/abs/2407.09297
We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifolds. The existing approaches to learning a distribution on arbitrary manifolds are expensive at inference time, since sampling requires solving a differentia
Externí odkaz:
http://arxiv.org/abs/2312.09852
Normalizing Flows are generative models that directly maximize the likelihood. Previously, the design of normalizing flows was largely constrained by the need for analytical invertibility. We overcome this constraint by a training procedure that uses
Externí odkaz:
http://arxiv.org/abs/2310.16624
Autor:
Sorrenson, Peter, Draxler, Felix, Rousselot, Armand, Hummerich, Sander, Zimmermann, Lea, Köthe, Ullrich
Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data. However, real data is typically only supported on a lower-dimensional manifold leading the model to expend significant compute on modeling noise. Injective Flow
Externí odkaz:
http://arxiv.org/abs/2306.01843
Autor:
Butter, Anja, Huetsch, Nathan, Schweitzer, Sofia Palacios, Plehn, Tilman, Sorrenson, Peter, Spinner, Jonas
We introduce two diffusion models and an autoregressive transformer for LHC physics simulations. Bayesian versions allow us to control the networks and capture training uncertainties. After illustrating their different density estimation methods for
Externí odkaz:
http://arxiv.org/abs/2305.10475
Autoencoders are an effective analysis tool for the LHC, as they represent one of its main goal of finding physics beyond the Standard Model. The key challenge is that out-of-distribution anomaly searches based on the compressibility of features do n
Externí odkaz:
http://arxiv.org/abs/2206.14225
Autor:
Dillon, Barry M., Kasieczka, Gregor, Olischlager, Hans, Plehn, Tilman, Sorrenson, Peter, Vogel, Lorenz
Publikováno v:
SciPost Phys. 12, 188 (2022)
Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is new-physics agnostic. We introduce Je
Externí odkaz:
http://arxiv.org/abs/2108.04253
Publikováno v:
SciPost Phys. 11, 061 (2021)
Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction, extracting jets with higher complexity but not the other way around. To address this, we derive classifiers from the latent spa
Externí odkaz:
http://arxiv.org/abs/2104.08291
A central question of representation learning asks under which conditions it is possible to reconstruct the true latent variables of an arbitrarily complex generative process. Recent breakthrough work by Khemakhem et al. (2019) on nonlinear ICA has a
Externí odkaz:
http://arxiv.org/abs/2001.04872
Autor:
Sorrenson, Peter James.
Publikováno v:
Access electronically.
Thesis (Ph.D.)--University of Wollongong, 2003.
Includes appendices. Typescript. Bibliographical references: leaf 216-227.
Includes appendices. Typescript. Bibliographical references: leaf 216-227.