Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Teh, YW"'
Score-based generative models (SGMs) are a powerful class of generative models that exhibit remarkable empirical performance. Score-based generative modelling (SGM) consists of a ``noising'' stage, whereby a diffusion is used to gradually add Gaussia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::600147ab3c626478e25d2b8c8989388f
http://arxiv.org/abs/2202.02763
http://arxiv.org/abs/2202.02763
Generative models are typically trained on grid-like data such as images. As a result, the size of these models usually scales directly with the underlying grid resolution. In this paper, we abandon discretized grids and instead parameterize individu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dcbea73d890162635b560432a994e213
Neural information processing systems foundation. All rights reserved. Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8a58aca0985ad5d6f2398021287f8f35
https://ora.ox.ac.uk/objects/uuid:0cfdde8d-8b0b-440a-97b7-7d2a185d1ad6
https://ora.ox.ac.uk/objects/uuid:0cfdde8d-8b0b-440a-97b7-7d2a185d1ad6
Objects are composed of a set of geometrically organized parts. We introduce an unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships between parts to reason about objects. Since these relationships do not depend on t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1064::11ff9499183fe51793a5f3738cc7735b
https://ora.ox.ac.uk/objects/uuid:95564c2c-5afb-46f8-b509-a60da6a15375
https://ora.ox.ac.uk/objects/uuid:95564c2c-5afb-46f8-b509-a60da6a15375
The Variational Auto-Encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot efficient
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1064::adce366211330467cceba9d622e41c44
https://ora.ox.ac.uk/objects/uuid:b2731bc0-f064-4f99-8b4e-4c7592f04b18
https://ora.ox.ac.uk/objects/uuid:b2731bc0-f064-4f99-8b4e-4c7592f04b18
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::024de774cb677071935ae03c4907338c
http://arxiv.org/abs/1912.02738
http://arxiv.org/abs/1912.02738
Autor:
Naderiparizi, S, Scibior, A, Munk, A, Ghadiri, M, Güneş Baydin, A, Gram-Hansen, B, Schroeder de Witt, C, Zinkov, R, Torr, PHS, Rainforth, T, Teh, YW, Wood, F
Naive approaches to amortized inference in probabilistic programs with unbounded loops can produce estimators with infinite variance. This is particularly true of importance sampling inference in programs that explicitly include rejection sampling as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a127fed03257ddb282757dd938aa69a0
http://arxiv.org/abs/1910.09056
http://arxiv.org/abs/1910.09056
Autor:
Galashov, A, Jayakumar, SM, Hasenclever, L, Tirumala, D, Schwarz, J, Desjardins, G, Czarnecki, WM, Teh, YW, Pascanu, R, Heess, N
Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning. We start from the KL
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bee681c2a811d4a8ce0e8cac42a6add3
http://arxiv.org/abs/1905.01240
http://arxiv.org/abs/1905.01240
Autor:
Bloem-Reddy, B, Teh, YW
Treating neural network inputs and outputs as random variables, we characterize the structure of neural networks that can be used to model data that are invariant or equivariant under the action of a compact group. Much recent research has been devot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e7b9f5e87c6e38bdee25b0d34193971e
http://arxiv.org/abs/1901.06082
http://arxiv.org/abs/1901.06082
Current meta-learning approaches focus on learning functional representations of relationships between variables, i.e. on estimating conditional expectations in regression. In many applications, however, we are faced with conditional distributions wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc25b00d636440806660e94b8e9edafa