paper-with-me

홈 › Papers

The Hidden Convex Optimization Landscape of Two-Layer ReLU Neural Networks: an Exact Characterization of the Optimal Solutions

2020-06-10 · Yifei Wang, Jonathan Lacotte, Mert Pilanci

We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and does not leverage duality-based analysis which was recently used to lift neural network training into convex spaces. Given the set of solutions of our convex optimization program, we show how to construct exactly the entire set of optimal neural networks. We provide a detailed characterization of this optimal set and its invariant transformations. As additional consequences of our convex perspective, (i) we establish that Clarke stationary points found by stochastic gradient descent correspond to the global optimum of a subsampled convex problem (ii) we provide a polynomial-time algorithm for checking if a neural network is a global minimum of the training loss (iii) we provide an explicit construction of a continuous path between any neural network and the global minimum of its sublevel set and (iv) characterize the minimal size of the hidden layer so that the neural network optimization landscape has no spurious valleys. Overall, we provide a rich framework for studying the landscape of neural network training loss through convexity.

📄 PDF Abstract BibTeX arXiv:2006.05900

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Weight Decay 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…

Similar Papers 제목 키워드 기반

The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions

2021-09-29 · ICLR 2022 4 · Yifei Wang, Jonathan Lacotte, Mert Pilanci

We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and d…

Unveiling Hidden Convexity in Deep Learning: a Sparse Signal Processing Perspective

2026-03-25 · Emi Zeger, Mert Pilanci arxiv

Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognition, audio processi…

Efficient Global Optimization of Two-layer ReLU Networks: Quadratic-time Algorithms and Adversarial Training

2022-01-06 · Yatong Bai, Tanmay Gautam, Somayeh Sojoudi

The non-convexity of the artificial neural network (ANN) training landscape brings inherent optimization difficulties. While the traditional back-propagation stochastic gradient descent (SGD) algorithm and its variants a…

global-optimization

Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?

2020-06-10 · Lifu Wang, Bo Shen, Ning Zhao, Zhiyuan Zhang

The residual network is now one of the most effective structures in deep learning, which utilizes the skip connections to ``guarantee" the performance will not get worse. However, the non-convexity of the neural network …

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy

2024-07-05 · Rob Romijnders, Antti Koskela

The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate states during training. However, the cur…