33 citations · 64 across the 9 of their papers we have counts for
10 papers
Bridging the Gap Between Target Networks and Functional Regularization
Alexandre Piche, Valentin Thomas, Joseph Marino +4
Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-ch…
Insights from Generative Modeling for Neural Video Compression
Ruihan Yang, Yibo Yang, Joseph Marino +1
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this wor…
Bridging the Gap Between Target Networks and Functional Regularization
Alexandre Piché, Valentin Thomas, Rafael Pardinas +4
Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-ch…
Predictive Coding, Variational Autoencoders, and Biological Connections
Joseph Marino
This paper reviews predictive coding, from theoretical neuroscience, and variational autoencoders, from machine learning, identifying the common origin and mathematical framework u…
Iterative Amortized Policy Optimization
Joseph Marino, Alexandre Piché, Alessandro Davide Ialongo +1
Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the va…
Hierarchical Autoregressive Modeling for Neural Video Compression
Ruihan Yang, Yibo Yang, Joseph Marino +1
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.…
Improving Sequential Latent Variable Models with Autoregressive Flows
Joseph Marino, Lei Chen, Jiawei He +1
We propose an approach for improving sequence modeling based on autoregressive normalizing flows. Each autoregressive transform, acting across time, serves as a moving frame of ref…
A General Method for Amortizing Variational Filtering
Joseph Marino, Milan Cvitkovic, Yisong Yue
We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information fro…
Iterative Amortized Inference
Joseph Marino, Yisong Yue, Stephan Mandt
Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By repla…
Probabilistic Video Generation using Holistic Attribute Control
Jiawei He, Andreas Lehrmann, Joseph Marino +2
Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identit…