paper-with-me

Papers

Provable Lipschitz Certification for Generative Models

2021-07-06 · Matt Jordan, Alexandros G. Dimakis

We present a scalable technique for upper bounding the Lipschitz constant of generative models. We relate this quantity to the maximal norm over the set of attainable vector-Jacobian products of a given generative model. We approximate this set by layerwise convex approximations using zonotopes. Our approach generalizes and improves upon prior work using zonotope transformers and we extend to Lipschitz estimation of neural networks with large output dimension. This provides efficient and tight bounds on small networks and can scale to generative models on VAE and DCGAN architectures.

📄 PDF Abstract BibTeX arXiv:2107.02732

Code (1)

revbucket/lipMIP 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
DCGAN 설명 없음

Similar Papers 제목 키워드 기반

Provably Robust Adaptation for Language-Empowered Foundation Models

2025-10-09 · Yuni Lai, Xiaoyu Xue, Linghui Shen, Yulun Wu 외 arxiv

Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations, enabling powerful downstream capabilitie…

Few-Shot Learning

CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models

2024-05-13 · Qilin Zhou, Zhengyuan Wei, Haipeng Wang, Bo Jiang 외

Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to la…

Semialgebraic Optimization for Lipschitz Constants of ReLU Networks

2020-02-10 · NeurIPS 2020 12 · Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels

The Lipschitz constant of a network plays an important role in many applications of deep learning, such as robustness certification and Wasserstein Generative Adversarial Network. We introduce a semidefinite programming …

Adversarial Robustness

Reward Certification for Policy Smoothed Reinforcement Learning

2023-12-11 · Ronghui Mu, Leandro Soriano Marcolino, Tianle Zhang, Yanghao Zhang 외

Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed policies" in order to enhance its robustness. …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks

2025-12-09 · Shihao Li, Jiachen Li, Dongmei Chen arxiv

Data attribution methods identify which training examples are responsible for a model's predictions, but their sensitivity to distributional perturbations undermines practical reliability. We present a unified framework …

Anomaly Detection