paper-with-me

Papers

Spectrum Extraction and Clipping for Implicitly Linear Layers

2024-02-25 · Ali Ebrahimpour Boroojeny, Matus Telgarsky, Hari Sundaram

We show the effectiveness of automatic differentiation in efficiently and correctly computing and controlling the spectrum of implicitly linear operators, a rich family of layer types including all standard convolutional and dense layers. We provide the first clipping method which is correct for general convolution layers, and illuminate the representational limitation that caused correctness issues in prior work. We study the effect of the batch normalization layers when concatenated with convolutional layers and show how our clipping method can be applied to their composition. By comparing the accuracy and performance of our algorithms to the state-of-the-art methods, using various experiments, we show they are more precise and efficient and lead to better generalization and adversarial robustness. We provide the code for using our methods at https://github.com/Ali-E/FastClip.

📄 PDF Abstract BibTeX arXiv:2402.16017

Code (1)

ali-e/fastclip 공식 구현 pytorch

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
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…

Similar Papers 제목 키워드 기반

Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed bandits

2023-05-11 · Yuriy Dorn, Nikita Kornilov, Nikolay Kutuzov, Alexander Nazin 외

The Implicitly Normalized Forecaster (INF) algorithm is considered to be an optimal solution for adversarial multi-armed bandit (MAB) problems. However, most of the existing complexity results for INF rely on restrictive…

Multi-Armed Bandits

Image to Image Translation based on Convolutional Neural Network Approach for Speech Declipping

2019-10-26

Clipping, as a current nonlinear distortion, often occurs due to the limited dynamic range of audio recorders. It degrades the speech quality and intelligibility and adversely affects the performances of speech and speak…

Image-to-Image TranslationTranslation

ManifoldFlow: SPD-Relaxed Stiefel Layers with Learnable Singular Spectrum

2026-07-05 · Haiwen Yi, Xinyuan Song arxiv

Orthogonal and Stiefel layers give neural weights exact spectral control, but they also impose a strong modeling constraint: all represented singular values are fixed at one. Many settings that benefit from an orthonorma…

Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters

2026-05-12 · Alexander Yukhimchuk, Mladen Kolar, Martin Takáč, Sayantan Choudhury arxiv

Gradient clipping is a standard safeguard for training neural networks under noisy, heavy-tailed stochastic gradients; yet, most clipping rules treat all parameters as vectors and ignore the matrix structure of modern ar…

Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descent

2023-07-21 · Toan N. Nguyen, Phuong Ha Nguyen, Lam M. Nguyen, Marten van Dijk

Each round in Differential Private Stochastic Gradient Descent (DPSGD) transmits a sum of clipped gradients obfuscated with Gaussian noise to a central server which uses this to update a global model which often represen…