Zobrazeno 1 - 10
of 4 261
pro vyhledávání: '"Cresswell, P"'
Autor:
Kowalczuk, Antoni, Dubiński, Jan, Ghomi, Atiyeh Ashari, Sui, Yi, Stein, George, Wu, Jiapeng, Cresswell, Jesse C., Boenisch, Franziska, Dziedzic, Adam
Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single task, name
Externí odkaz:
http://arxiv.org/abs/2407.12588
Autor:
Kamkari, Hamidreza, Ross, Brendan Leigh, Hosseinzadeh, Rasa, Cresswell, Jesse C., Loaiza-Ganem, Gabriel
High-dimensional data commonly lies on low-dimensional submanifolds, and estimating the local intrinsic dimension (LID) of a datum -- i.e. the dimension of the submanifold it belongs to -- is a longstanding problem. LID can be understood as the numbe
Externí odkaz:
http://arxiv.org/abs/2406.03537
We study the generation of fermion mass in a context where interactions break a discrete chiral symmetry. Then, fermion mass is not protected by a symmetry, no symmetry is broken by the generation of mass, and a vanishing mass no longer enhances a sy
Externí odkaz:
http://arxiv.org/abs/2406.00100
Autor:
Loaiza-Ganem, Gabriel, Ross, Brendan Leigh, Hosseinzadeh, Rasa, Caterini, Anthony L., Cresswell, Jesse C.
In recent years there has been increased interest in understanding the interplay between deep generative models (DGMs) and the manifold hypothesis. Research in this area focuses on understanding the reasons why commonly-used DGMs succeed or fail at l
Externí odkaz:
http://arxiv.org/abs/2404.02954
Autor:
Kamkari, Hamidreza, Ross, Brendan Leigh, Cresswell, Jesse C., Caterini, Anthony L., Krishnan, Rahul G., Loaiza-Ganem, Gabriel
Likelihood-based deep generative models (DGMs) commonly exhibit a puzzling behaviour: when trained on a relatively complex dataset, they assign higher likelihood values to out-of-distribution (OOD) data from simpler sources. Adding to the mystery, OO
Externí odkaz:
http://arxiv.org/abs/2403.18910
In response to everyday queries, humans explicitly signal uncertainty and offer alternative answers when they are unsure. Machine learning models that output calibrated prediction sets through conformal prediction mimic this human behaviour; larger s
Externí odkaz:
http://arxiv.org/abs/2401.13744
Autor:
Vouitsis, Noël, Liu, Zhaoyan, Gorti, Satya Krishna, Villecroze, Valentin, Cresswell, Jesse C., Yu, Guangwei, Loaiza-Ganem, Gabriel, Volkovs, Maksims
The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive datasets of paired inputs and large-scale computational resources, mak
Externí odkaz:
http://arxiv.org/abs/2312.10144
Autor:
Sui, Yi, Wu, Tongzi, Cresswell, Jesse C., Wu, Ga, Stein, George, Huang, Xiao Shi, Zhang, Xiaochen, Volkovs, Maksims
Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. While augmentation-based SSRL algorithms push the boundaries of performanc
Externí odkaz:
http://arxiv.org/abs/2310.07756
Autor:
Karlbauer, Matthias, Cresswell-Clay, Nathaniel, Durran, Dale R., Moreno, Raul A., Kurth, Thorsten, Bonev, Boris, Brenowitz, Noah, Butz, Martin V.
We present a parsimonious deep learning weather prediction model to forecast seven atmospheric variables with 3-h time resolution for up to one-year lead times on a 110-km global mesh using the Hierarchical Equal Area isoLatitude Pixelization (HEALPi
Externí odkaz:
http://arxiv.org/abs/2311.06253
Autor:
Wu, Jiapeng, Ghomi, Atiyeh Ashari, Glukhov, David, Cresswell, Jesse C., Boenisch, Franziska, Papernot, Nicolas
Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified robustness are e
Externí odkaz:
http://arxiv.org/abs/2306.08656