paper-with-me

홈 › Papers

Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks

2020-02-24 · ICML 2020 1 · Mert Pilanci, Tolga Ergen

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden neurons. Our theory utilizes semi-infinite duality and minimum norm regularization. We show that ReLU networks trained with standard weight decay are equivalent to block $\ell_1$ penalized convex models. Moreover, we show that certain standard convolutional linear networks are equivalent semi-definite programs which can be simplified to $\ell_1$ regularized linear models in a polynomial sized discrete Fourier feature space.

📄 PDF Abstract BibTeX arXiv:2002.10553

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

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…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time

2020-06-26 · ICLR 2021 1 · Tolga Ergen, Mert Pilanci

We study training of Convolutional Neural Networks (CNNs) with ReLU activations and introduce exact convex optimization formulations with a polynomial complexity with respect to the number of data samples, the number of …

Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully Polynomial-Time

2021-01-07 · Burak Bartan, Mert Pilanci

The training of two-layer neural networks with nonlinear activation functions is an important non-convex optimization problem with numerous applications and promising performance in layerwise deep learning. In this paper…

global-optimization

Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators

2015-03-11 · Yuchen Zhang, Martin J. Wainwright, Michael. I. Jordan

For the problem of high-dimensional sparse linear regression, it is known that an $\ell_0$-based estimator can achieve a $1/n$ "fast" rate on the prediction error without any conditions on the design matrix, whereas in a…

Provably Convergent Working Set Algorithm for Non-Convex Regularized Regression

2020-06-24 · Alain Rakotomamonjy, Rémi Flamary, Gilles Gasso, Joseph Salmon

Owing to their statistical properties, non-convex sparse regularizers have attracted much interest for estimating a sparse linear model from high dimensional data. Given that the solution is sparse, for accelerating conv…

regression

Efficient Learning with a Family of Nonconvex Regularizers by Redistributing Nonconvexity

2016-06-13 · Quanming Yao, James T. Kwok

The use of convex regularizers allows for easy optimization, though they often produce biased estimation and inferior prediction performance. Recently, nonconvex regularizers have attracted a lot of attention and outperf…