홈 › Papers

Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes

2020-07-02 · NeurIPS 2020 12 · Andrew Y. K. Foong, Wessel P. Bruinsma, Jonathan Gordon, Yann Dubois, James Requeima, Richard E. Turner

Stationary stochastic processes (SPs) are a key component of many probabilistic models, such as those for off-the-grid spatio-temporal data. They enable the statistical symmetry of underlying physical phenomena to be leveraged, thereby aiding generalization. Prediction in such models can be viewed as a translation equivariant map from observed data sets to predictive SPs, emphasizing the intimate relationship between stationarity and equivariance. Building on this, we propose the Convolutional Neural Process (ConvNP), which endows Neural Processes (NPs) with translation equivariance and extends convolutional conditional NPs to allow for dependencies in the predictive distribution. The latter enables ConvNPs to be deployed in settings which require coherent samples, such as Thompson sampling or conditional image completion. Moreover, we propose a new maximum-likelihood objective to replace the standard ELBO objective in NPs, which conceptually simplifies the framework and empirically improves performance. We demonstrate the strong performance and generalization capabilities of ConvNPs on 1D regression, image completion, and various tasks with real-world spatio-temporal data.

📄 PDF Abstract BibTeX arXiv:2007.01332

Code (2)

YannDubs/Neural-Process-Family 공식 구현 pytorch

wesselb/NeuralProcesses.jl 공식 구현

Tasks

Meta-LearningThompson SamplingTranslation

Meta-descent for Online, Continual Prediction

2019-07-17 · Andrew Jacobsen, Matthew Schlegel, Cameron Linke, Thomas Degris 외

This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update wi…

Prediction Second-order methods Time Series Time Series Analysis+1

MetaCURL: Non-stationary Concave Utility Reinforcement Learning

2024-05-30 · Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane

We explore online learning in episodic loop-free Markov decision processes on non-stationary environments (changing losses and probability transitions). Our focus is on the Concave Utility Reinforcement Learning problem …

reinforcement-learning Reinforcement Learning

On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning

2020-02-12 · NeurIPS 2021 12 · Alireza Fallah, Kristian Georgiev, Aryan Mokhtari, Asuman Ozdaglar

We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcement Learning (RL) problems, where the goal is to find a policy using data from several tasks represented by Markov Decision Processes (MDPs) that can …

Meta-Learning Meta Reinforcement Learning Policy Gradient Methods reinforcement-learning+2

Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction

2025-06-05 · Yuanpei Gao, Qi Yan, Yan Leng, Renjie Liao

While deep learning methods have achieved strong performance in time series prediction, their black-box nature and inability to explicitly model underlying stochastic processes often limit their generalization to non-sta…

Time Series Time Series Prediction

The Forget-me-not Process

2016-12-01 · NeurIPS 2016 12 · Kieran Milan, Joel Veness, James Kirkpatrick, Michael Bowling 외

We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources. Our method works by taking a Bayesian approach…

Prediction