paper-with-me

Papers

Deep Neural Networks as Iterated Function Systems and a Generalization Bound

2026-01-27 · Jonathan Vacher arxiv

Deep neural networks (DNNs) achieve remarkable performance on a wide range of tasks, yet their mathematical analysis remains fragmented: stability and generalization are typically studied in disparate frameworks and on a case-by-case basis. Architecturally, DNNs rely on the recursive application of parametrized functions, a mechanism that can be unstable and difficult to train, making stability a primary concern. Even when training succeeds, there are few rigorous results on how well such models generalize beyond the observed data, especially in the generative setting. In this work, we leverage the theory of stochastic Iterated Function Systems (IFS) and show that two important deep architectures can be viewed as, or canonically associated with, place-dependent IFS. This connection allows us to import results from random dynamical systems to (i) establish the existence and uniqueness of invariant measures under suitable contractivity assumptions, and (ii) derive a Wasserstein generalization bound for generative modeling. The bound naturally leads to a new training objective that directly controls the collage-type approximation error between the data distribution and its image under the learned transfer operator. We illustrate the theory on a controlled 2D example and empirically evaluate the proposed objective on standard image datasets (MNIST, CelebA, CIFAR-10).

📄 PDF Abstract BibTeX arXiv:2601.19958

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Image Compression predicated on Recurrent Iterated Function Systems

2013-04-07 · Chol-Hui Yun, W. Metzler, M. Barski

Recurrent iterated function systems (RIFSs) are improvements of iterated function systems (IFSs) using elements of the theory of Marcovian stochastic processes which can produce more natural looking images. We construct …

Image Compression

Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms

2021-06-09 · NeurIPS 2021 12 · Alexander Camuto, George Deligiannidis, Murat A. Erdogdu, Mert Gürbüzbalaban 외

Understanding generalization in deep learning has been one of the major challenges in statistical learning theory over the last decade. While recent work has illustrated that the dataset and the training algorithm must b…

Generalization BoundsLearning TheoryStochastic Optimization

Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback

2023-07-06 · Yu Chen, Yihan Du, Pihe Hu, Siwei Wang 외

Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that employs an Iterated Conditional Value-at-…

Decision MakingLEMMAreinforcement-learningReinforcement Learning (RL)

Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path

2022-06-06 · Yihan Du, Siwei Wang, Longbo Huang

In this paper, we study a novel episodic risk-sensitive Reinforcement Learning (RL) problem, named Iterated CVaR RL, which aims to maximize the tail of the reward-to-go at each step, and focuses on tightly controlling th…

Autonomous Drivingreinforcement-learningReinforcement Learning (RL)

Rademacher Complexity of Neural ODEs via Chen-Fliess Series

2024-01-30 · Joshua Hanson, Maxim Raginsky

We show how continuous-depth neural ODE models can be framed as single-layer, infinite-width nets using the Chen--Fliess series expansion for nonlinear ODEs. In this net, the output ``weights'' are taken from the signatu…