paper-with-me

홈 › Papers

A visual exploration of Gaussian Processes and Infinite Neural Networks

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

Gaussian Processes generalize Gaussian distributions to functons as random variables (stochastic processes). As such, they are a powerful tool for regression and Bayesian inference. In the last years, they have received increased attention due to the interest in machine learning. An interesting connection between Gaussian Processes and Neural Networks exists when the width of feed-forward neural networks tends towards infinity. For a specific choice of priors over the network parameters, the resulting network samples will be distributed according to a Gaussian Process. In this blog post, I intend to explore this connection between Gaussian Processes and infinite Neural Nets, using Julia code and visual examples. I believe that there is some value in creating an intuitive understanding of the connection between those two methods as Gaussian Processes may help us understand how well Neural Networks can perform in the limit of infinite neurons per layer. Moreover, they may do so while keeping the probabilistic nature of the process in mind, as network training and the resulting performance will heavily depend on the initialization of the network weights. Finally, I discuss the limitations of this approach and how it may be extended by using Bayesian Neural Networks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceGaussian Processes

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Optimal Reinforcement Learning for Gaussian Systems

2011-12-01 · NeurIPS 2011 12 · Philipp Hennig

The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optim…

Gaussian Processesreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Infinite Mixtures of Multivariate Gaussian Processes

2013-07-26 · Shiliang Sun

This paper presents a new model called infinite mixtures of multivariate Gaussian processes, which can be used to learn vector-valued functions and applied to multitask learning. As an extension of the single multivariat…

Gaussian Processesregression

Student-t processes as infinite-width limits of posterior Bayesian neural networks

2025-02-06 · Francesco Caporali, Stefano Favaro, Dario Trevisan

The asymptotic properties of Bayesian Neural Networks (BNNs) have been extensively studied, particularly regarding their approximations by Gaussian processes in the infinite-width limit. We extend these results by showin…

Gaussian Processes

Deep learning with differential Gaussian process flows

2018-10-09 · Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of diffe…

Deep LearningGaussian ProcessesGeneral Classificationregression

Scale Mixtures of Neural Network Gaussian Processes

2021-07-03 · ICLR 2022 4 · Hyungi Lee, Eunggu Yun, Hongseok Yang, Juho Lee

Recent works have revealed that infinitely-wide feed-forward or recurrent neural networks of any architecture correspond to Gaussian processes referred to as Neural Network Gaussian Processes (NNGPs). While these works h…

Gaussian Processes