paper-with-me

Papers

Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constant

2020-01-17 · Shayan Aziznejad, Harshit Gupta, Joaquim Campos, Michael Unser

We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output relation. To that end, we first establish a global bound for the Lipschitz constant of neural networks. Based on the obtained bound, we then formulate a variational problem for learning activation functions. Our variational problem is infinite-dimensional and is not computationally tractable. However, we prove that there always exists a solution that has continuous and piecewise-linear (linear-spline) activations. This reduces the original problem to a finite-dimensional minimization where an l1 penalty on the parameters of the activations favors the learning of sparse nonlinearities. We numerically compare our scheme with standard ReLU network and its variations, PReLU and LeakyReLU and we empirically demonstrate the practical aspects of our framework.

📄 PDF Abstract BibTeX arXiv:2001.06263

Code (1)

jloveric/high-order-layers-torch 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…
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…
PReLU A Parametric Rectified Linear Unit, or PReLU, is an activation function that generalizes the traditional rectified unit with a slope for negative values.…

Similar Papers 제목 키워드 기반

ExLipBaB: Exact Lipschitz Constant Computation for Piecewise Linear Neural Networks

2026-02-17 · Tom A. Splittgerber arxiv

It has been shown that a neural network's Lipschitz constant can be leveraged to derive robustness guarantees, to improve generalizability via regularization or even to construct invertible networks. Therefore, a number …

Local Lipschitz Bounds of Deep Neural Networks

2020-04-27 · Calypso Herrera, Florian Krach, Josef Teichmann

The Lipschitz constant is an important quantity that arises in analysing the convergence of gradient-based optimization methods. It is generally unclear how to estimate the Lipschitz constant of a complex model. Thus, th…

Lipschitz-aware Linearity Grafting for Certified Robustness

2025-10-29 · Yongjin Han, Suhyun Kim arxiv

Lipschitz constant is a fundamental property in certified robustness, as smaller values imply robustness to adversarial examples when a model is confident in its prediction. However, identifying the worst-case adversaria…

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

2021-11-02 · NeurIPS 2021 12 · Yujia Huang, huan zhang, Yuanyuan Shi, J Zico Kolter 외

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschi…

Simultaneously Solving Infinitely Many LQ Mean Field Games In Hilbert Spaces: The Power of Neural Operators

2025-10-22 · Dena Firoozi, Anastasis Kratsios, Xuwei Yang arxiv

Traditional mean-field game (MFG) solvers operate on an instance-by-instance basis, which becomes infeasible when many related problems must be solved (e.g., for seeking a robust description of the solution under perturb…