paper-with-me

Papers

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

2023-02-17 · Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance. Our first result on the Wasserstein distance assumes the instance space is bounded, while our second result takes advantage of dimensionality reduction. Our results naturally apply to Wasserstein GANs and Energy-Based GANs, and our bounds provide new training objectives for these two. Although our work is mainly theoretical, we perform numerical experiments showing non-vacuous generalization bounds for Wasserstein GANs on synthetic datasets.

📄 PDF Abstract BibTeX arXiv:2302.08942

Code (1)

diarra2339/pac-bayes-wgan 공식 구현 pytorch

Tasks

Dimensionality ReductionGeneralization Bounds

Similar Papers 제목 키워드 기반

PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Network

2024-02-06 · Tan Sun, Junhong Lin

Graph neural networks (GNNs) have gained popularity for various graph-related tasks. However, similar to deep neural networks, GNNs are also vulnerable to adversarial attacks. Empirical studies have shown that adversaria…

Generalization BoundsGraph Neural Network

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

2023-10-09 · NeurIPS 2023 11

Deep neural networks (DNNs) are vulnerable to adversarial attacks. It is found empirically that adversarially robust generalization is crucial in establishing defense algorithms against adversarial attacks. Therefore, it…

Adversarial RobustnessGeneralization Bounds

A PAC-Bayes Analysis of Adversarial Robustness

2021-02-19 · NeurIPS 2021 12 · Paul Viallard, Guillaume Vidot, Amaury Habrard, Emilie Morvant

We propose the first general PAC-Bayesian generalization bounds for adversarial robustness, that estimate, at test time, how much a model will be invariant to imperceptible perturbations in the input. Instead of deriving…

Adversarial RobustnessGeneralization Boundsvalid

PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons

2020-06-16 · Xinjie Lan, Xin Guo, Kenneth E. Barner

We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspects: (i) MLPs formulate a family of Gibbs …

Generalization BoundsVariational Inference

Misclassification excess risk bounds for PAC-Bayesian classification via convexified loss

2024-08-16 · The Tien Mai

PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with …

Generalization Bounds