Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Goliński, Adam"'
Autor:
Blaas, Arno, Goliński, Adam, Miller, Andrew, Zappella, Luca, Jacobsen, Jörn-Henrik, Heinze-Deml, Christina
We consider robustness to distribution shifts in the context of diagnostic models in healthcare, where the prediction target $Y$, e.g., the presence of a disease, is causally upstream of the observations $X$, e.g., a biomarker. Distribution shifts ma
Externí odkaz:
http://arxiv.org/abs/2410.19575
Autor:
Rodríguez-Gálvez, Borja, Blaas, Arno, Rodríguez, Pau, Goliński, Adam, Suau, Xavier, Ramapuram, Jason, Busbridge, Dan, Zappella, Luca
The mechanisms behind the success of multi-view self-supervised learning (MVSSL) are not yet fully understood. Contrastive MVSSL methods have been studied through the lens of InfoNCE, a lower bound of the Mutual Information (MI). However, the relatio
Externí odkaz:
http://arxiv.org/abs/2307.10907
Autor:
Tempczyk, Piotr, Michaluk, Rafał, Garncarek, Łukasz, Spurek, Przemysław, Tabor, Jacek, Goliński, Adam
Most of the existing methods for estimating the local intrinsic dimension of a data distribution do not scale well to high-dimensional data. Many of them rely on a non-parametric nearest neighbors approach which suffers from the curse of dimensionali
Externí odkaz:
http://arxiv.org/abs/2206.14882
Autor:
Dupont, Emilien, Loya, Hrushikesh, Alizadeh, Milad, Goliński, Adam, Teh, Yee Whye, Doucet, Arnaud
Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly handles a wid
Externí odkaz:
http://arxiv.org/abs/2201.12904
We show that the standard computational pipeline of probabilistic programming systems (PPSs) can be inefficient for estimating expectations and introduce the concept of expectation programming to address this. In expectation programming, the aim of t
Externí odkaz:
http://arxiv.org/abs/2106.04953
We propose a new simple approach for image compression: instead of storing the RGB values for each pixel of an image, we store the weights of a neural network overfitted to the image. Specifically, to encode an image, we fit it with an MLP which maps
Externí odkaz:
http://arxiv.org/abs/2103.03123
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video compression s
Externí odkaz:
http://arxiv.org/abs/2004.04342
Current approaches to amortizing Bayesian inference focus solely on approximating the posterior distribution. Typically, this approximation is, in turn, used to calculate expectations for one or more target functions - a computational pipeline which
Externí odkaz:
http://arxiv.org/abs/1907.08082
Autor:
Webb, Stefan, Golinski, Adam, Zinkov, Robert, Siddharth, N., Rainforth, Tom, Teh, Yee Whye, Wood, Frank
Inference amortization methods share information across multiple posterior-inference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modelle
Externí odkaz:
http://arxiv.org/abs/1712.00287
