From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networks
The connection between Residual Neural Networks (ResNets) and continuous-time control systems (known as NeurODEs) has led to a mathematical analysis of neural networks which has provided interesting results of both theoretical and practical significance. However, by construction, NeurODEs have been limited to describing constant-width layers, making them unsuitable for modeling deep learning architectures with layers of variable width. In this paper, we propose a continuous-time Autoencoder, which we call AutoencODE, based on a modification of the controlled field that drives the dynamics. This adaptation enables the extension of the mean-field control framework originally devised for conventional NeurODEs. In this setting, we tackle the case of low Tikhonov regularization, resulting in potentially non-convex cost landscapes. While the global results obtained for high Tikhonov regularization may not hold globally, we show that many of them can be recovered in regions where the loss function is locally convex. Inspired by our theoretical findings, we develop a training method tailored to this specific type of Autoencoders with residual connections, and we validate our approach through numerical experiments conducted on various examples.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Variational Lossy Autoencoder
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one…
Density EstimationImage GenerationRepresentation LearningDeep Representation Learning and Clustering of Traffic Scenarios
Determining the traffic scenario space is a major challenge for the homologation and coverage assessment of automated driving functions. In contrast to current approaches that are mainly scenario-based and rely on expert…
ClusteringRepresentation LearningRetrievalScalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control
In recent years, reinforcement learning and its multi-agent analogue have achieved great success in solving various complex control problems. However, multi-agent reinforcement learning remains challenging both in its th…
Collision AvoidanceMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces
We establish the convergence of the deep actor-critic reinforcement learning algorithm presented in [Angiuli et al., 2023a] in the setting of continuous state and action spaces with an infinite discrete-time horizon. Thi…
Reinforcement LearningMean Field Reinforcement Learning
This monograph provides an introduction to mean field reinforcement learning through the lens of Markov decision processes arising from large-population stochastic control with mean field interactions and common noise. S…
Multi-agent Reinforcement Learning