paper-with-me

홈 › Papers

Porcupine Neural Networks: (Almost) All Local Optima are Global

2017-10-05 · Soheil Feizi, Hamid Javadi, Jesse Zhang, David Tse

Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes their performance analysis challenging. In this paper, we take a novel approach to this problem by asking whether one can constrain neural network weights to make its optimization landscape have good theoretical properties while at the same time, be a good approximation for the unconstrained one. For two-layer neural networks, we provide affirmative answers to these questions by introducing Porcupine Neural Networks (PNNs) whose weight vectors are constrained to lie over a finite set of lines. We show that most local optima of PNN optimizations are global while we have a characterization of regions where bad local optimizers may exist. Moreover, our theoretical and empirical results suggest that an unconstrained neural network can be approximated using a polynomially-large PNN.

📄 PDF Abstract BibTeX arXiv:1710.02196

Code (1)

jessemzhang/porcupine_neural_networks tf

Tasks

All

Similar Papers 제목 키워드 기반

Porcupine Neural Networks: Approximating Neural Network Landscapes

2018-12-01 · NeurIPS 2018 12 · Soheil Feizi, Hamid Javadi, Jesse Zhang, David Tse

Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes analyzing their performance challen…

The loss surface of deep and wide neural networks

2017-04-26 · ICML 2017 8 · Quynh Nguyen, Matthias Hein

While the optimization problem behind deep neural networks is highly non-convex, it is frequently observed in practice that training deep networks seems possible without getting stuck in suboptimal points. It has been ar…

Federated reinforcement learning for robot motion planning with zero-shot generalization

2024-03-20 · Zhenyuan Yuan, Siyuan Xu, Minghui Zhu

This paper considers the problem of learning a control policy for robot motion planning with zero-shot generalization, i.e., no data collection and policy adaptation is needed when the learned policy is deployed in new e…

Motion PlanningZero-shot Generalization

Global Minimum Energy State Estimation for Embedded Nonlinear Systems with Symmetry

2024-09-13 · Pieter van Goor, Robert Mahony

Choosing a nonlinear state estimator for an application often involves a trade-off between local optimality (such as provided by an extended Kalman filter) and (almost-/semi-) global asymptotic stability (such as provide…

State Estimation

Small nonlinearities in activation functions create bad local minima in neural networks

2018-02-10 · ICLR 2019 5 · Chulhee Yun, Suvrit Sra, Ali Jadbabaie

We investigate the loss surface of neural networks. We prove that even for one-hidden-layer networks with "slightest" nonlinearity, the empirical risks have spurious local minima in most cases. Our results thus indicate …