English
Related papers

Related papers: Adversarially Contrastive Estimation of Conditiona…

200 papers

Conditional Neural Processes~(CNPs) bridge neural networks with probabilistic inference to approximate functions of Stochastic Processes under meta-learning settings. Given a batch of non-{\it i.i.d} function instantiations, CNPs are…

Machine Learning · Computer Science 2022-03-28 Zesheng Ye , Lina Yao

Conditional Neural Processes (CNP; Garnelo et al., 2018) are an attractive family of meta-learning models which produce well-calibrated predictions, enable fast inference at test time, and are trainable via a simple maximum likelihood…

Machine Learning · Computer Science 2021-10-19 Stratis Markou , James Requeima , Wessel Bruinsma , Richard Turner

Conditional neural processes (CNPs; Garnelo et al., 2018a) are attractive meta-learning models which produce well-calibrated predictions and are trainable via a simple maximum likelihood procedure. Although CNPs have many advantages, they…

The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance. However, the current CNP models only capture the overall…

Machine Learning · Computer Science 2022-12-02 Deep Shankar Pandey , Qi Yu

Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the…

Neural processes are a family of models which use neural networks to directly parametrise a map from data sets to predictions. Directly parametrising this map enables the use of expressive neural networks in small-data problems where neural…

Machine Learning · Statistics 2024-08-20 Wessel P. Bruinsma

Conditional Neural Processes (CNPs; Garnelo et al., 2018a) are meta-learning models which leverage the flexibility of deep learning to produce well-calibrated predictions and naturally handle off-the-grid and missing data. CNPs scale to…

Machine Learning · Statistics 2022-06-14 Stratis Markou , James Requeima , Wessel P. Bruinsma , Anna Vaughan , Richard E. Turner

Neural Processes (NPs) are a family of conditional generative models that are able to model a distribution over functions, in a way that allows them to perform predictions at test time conditioned on a number of context points. A recent…

Machine Learning · Computer Science 2021-06-14 Jens Petersen , Gregor Köhler , David Zimmerer , Fabian Isensee , Paul F. Jäger , Klaus H. Maier-Hein

Neural processes are a family of probabilistic models that inherit the flexibility of neural networks to parameterize stochastic processes. Despite providing well-calibrated predictions, especially in regression problems, and quick…

Machine Learning · Computer Science 2023-07-04 Peiman Mohseni , Nick Duffield , Bani Mallick , Arman Hasanzadeh

Conventional predictive Artificial Neural Networks (ANNs) commonly employ deterministic weight matrices; therefore, their prediction is a point estimate. Such a deterministic nature in ANNs causes the limitations of using ANNs for medical…

Machine Learning · Computer Science 2020-07-02 Minhyeok Lee , Junhee Seok

Neural Processes (NPs; Garnelo et al., 2018a,b) are a rich class of models for meta-learning that map data sets directly to predictive stochastic processes. We provide a rigorous analysis of the standard maximum-likelihood objective used to…

Machine Learning · Statistics 2021-01-12 Wessel P. Bruinsma , James Requeima , Andrew Y. K. Foong , Jonathan Gordon , Richard E. Turner

Training energy-based models (EBMs) with noise-contrastive estimation (NCE) is theoretically feasible but practically challenging. Effective learning requires the noise distribution to be approximately similar to the target distribution,…

Machine Learning · Computer Science 2022-11-07 Nathaniel Xu

Many parametric statistical models are not properly normalised and only specified up to an intractable partition function, which renders parameter estimation difficult. Examples of unnormalised models are Gibbs distributions, Markov random…

Machine Learning · Statistics 2018-06-12 Ciwan Ceylan , Michael U. Gutmann

Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers notice that robust models with AT have good generative ability and can synthesize realistic images, while…

Machine Learning · Computer Science 2022-03-28 Yifei Wang , Yisen Wang , Jiansheng Yang , Zhouchen Lin

Neural processes (NPs) are models for transfer learning with properties reminiscent of Gaussian Processes (GPs). They are adept at modelling data consisting of few observations of many related functions on the same input space and are…

Machine Learning · Statistics 2023-02-24 Miguel Garcia-Ortegon , Andreas Bender , Sergio Bacallado

Learning by contrasting positive and negative samples is a general strategy adopted by many methods. Noise contrastive estimation (NCE) for word embeddings and translating embeddings for knowledge graphs are examples in NLP employing this…

Computation and Language · Computer Science 2018-08-06 Avishek Joey Bose , Huan Ling , Yanshuai Cao

The consequences of complex disturbed environments in the vicinity of a supermassive black hole are not well represented by standard statistical models of optical variability in active galactic nuclei (AGN). Thus, developing new…

Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as in…

Obtaining reliable uncertainty estimates of neural network predictions is a long standing challenge. Bayesian neural networks have been proposed as a solution, but it remains open how to specify their prior. In particular, the common…

Machine Learning · Statistics 2019-07-02 Danijar Hafner , Dustin Tran , Timothy Lillicrap , Alex Irpan , James Davidson

Neural Processes (NPs) are meta-learning models that learn to map sets of observations to approximations of the corresponding posterior predictive distributions. By accommodating variable-sized, unstructured collections of observations and…

Machine Learning · Computer Science 2026-02-10 Peiman Mohseni , Nick Duffield
‹ Prev 1 2 3 10 Next ›