paper-with-me

홈 › Papers

From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networks

2023-07-05 · Cristina Cipriani, Massimo Fornasier, Alessandro Scagliotti

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.

📄 PDF Abstract BibTeX arXiv:2307.02279

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Variational Lossy Autoencoder

2016-11-08 · Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan 외

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 Learning

Deep Representation Learning and Clustering of Traffic Scenarios

2020-07-15 · Nick Harmening, Marin Biloš, Stephan Günnemann

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 LearningRetrieval

Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control

2022-09-15 · Kai Cui, Mengguang Li, Christian Fabian, Heinz Koeppl

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+1

Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces

2025-11-10 · Jean-Pierre Fouque, Mathieu Laurière, Mengrui Zhang arxiv

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 Learning

Mean Field Reinforcement Learning

2026-07-01 · René Carmona, Mathieu Laurière arxiv

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