Search Results for author: Alessandro Davide Ialongo

Found 6 papers, 2 papers with code

Iterative Amortized Policy Optimization

1 code implementation NeurIPS 2021 Joseph Marino, Alexandre Piché, Alessandro Davide Ialongo, Yisong Yue

Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions.

Continuous Control reinforcement-learning +2

Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models

1 code implementation13 Jun 2019 Alessandro Davide Ialongo, Mark van der Wilk, James Hensman, Carl Edward Rasmussen

As we demonstrate in our experiments, the factorisation between latent system states and transition function can lead to a miscalibrated posterior and to learning unnecessarily large noise terms.

Variational Inference

Non-Factorised Variational Inference in Dynamical Systems

no code implementations14 Dec 2018 Alessandro Davide Ialongo, Mark van der Wilk, James Hensman, Carl Edward Rasmussen

We focus on variational inference in dynamical systems where the discrete time transition function (or evolution rule) is modelled by a Gaussian process.

Variational Inference

Closed-form Inference and Prediction in Gaussian Process State-Space Models

no code implementations10 Dec 2018 Alessandro Davide Ialongo, Mark van der Wilk, Carl Edward Rasmussen

We examine an analytic variational inference scheme for the Gaussian Process State Space Model (GPSSM) - a probabilistic model for system identification and time-series modelling.

Time Series Time Series Analysis +1

Quantum machine learning: a classical perspective

no code implementations26 Jul 2017 Carlo Ciliberto, Mark Herbster, Alessandro Davide Ialongo, Massimiliano Pontil, Andrea Rocchetto, Simone Severini, Leonard Wossnig

Recently, increased computational power and data availability, as well as algorithmic advances, have led machine learning techniques to impressive results in regression, classification, data-generation and reinforcement learning tasks.

BIG-bench Machine Learning Quantum Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.