English
Related papers

Related papers: Neural Networks with Complex-Valued Weights Have N…

200 papers

Quantum Neural Networks (QNNs), or the so-called variational quantum circuits, are important quantum applications both because of their similar promises as classical neural networks and because of the feasibility of their implementation on…

Quantum Physics · Physics 2021-10-07 Xuchen You , Xiaodi Wu

In this paper we study shallow neural network functions which are linear combinations of compositions of activation and quadratic functions, replacing standard affine linear functions, often called neurons. We show the universality of this…

Numerical Analysis · Mathematics 2022-05-12 Leon Frischauf , Otmar Scherzer , Cong Shi

We identify a class of over-parameterized deep neural networks with standard activation functions and cross-entropy loss which provably have no bad local valley, in the sense that from any point in parameter space there exists a continuous…

Machine Learning · Computer Science 2018-12-27 Quynh Nguyen , Mahesh Chandra Mukkamala , Matthias Hein

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,…

Machine Learning · Statistics 2017-10-09 Soheil Feizi , Hamid Javadi , Jesse Zhang , David Tse

One of the main difficulties in analyzing neural networks is the non-convexity of the loss function which may have many bad local minima. In this paper, we study the landscape of neural networks for binary classification tasks. Under mild…

Machine Learning · Statistics 2018-05-23 Shiyu Liang , Ruoyu Sun , Jason D. Lee , R. Srikant

We study spurious second-order stationary points and local minima in a nonconvex low-rank formulation of sum-of-squares optimization on a real variety $X$. We reformulate the problem of finding a spurious local minimum in terms of syzygies…

Optimization and Control · Mathematics 2024-11-05 Grigoriy Blekherman , Rainer Sinn , Mauricio Velasco , Shixuan Zhang

We challenge the longstanding assumption that the mean-field approximation for variational inference in Bayesian neural networks is severely restrictive, and show this is not the case in deep networks. We prove several results indicating…

Machine Learning · Computer Science 2021-03-11 Sebastian Farquhar , Lewis Smith , Yarin Gal

Matrix completion is a basic machine learning problem that has wide applications, especially in collaborative filtering and recommender systems. Simple non-convex optimization algorithms are popular and effective in practice. Despite recent…

Machine Learning · Computer Science 2018-07-24 Rong Ge , Jason D. Lee , Tengyu Ma

Neural networks are usually not the tool of choice for nonparametric high-dimensional problems where the number of input features is much larger than the number of observations. Though neural networks can approximate complex multivariate…

Methodology · Statistics 2019-06-25 Jean Feng , Noah Simon

Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that…

Machine Learning · Computer Science 2017-03-06 Bo Xie , Yingyu Liang , Le Song

We use smoothed analysis techniques to provide guarantees on the training loss of Multilayer Neural Networks (MNNs) at differentiable local minima. Specifically, we examine MNNs with piecewise linear activation functions, quadratic loss and…

Machine Learning · Statistics 2016-05-31 Daniel Soudry , Yair Carmon

Neural networks provide a rich class of high-dimensional, non-convex optimization problems. Despite their non-convexity, gradient-descent methods often successfully optimize these models. This has motivated a recent spur in research…

Optimization and Control · Mathematics 2020-06-18 Luca Venturi , Afonso S. Bandeira , Joan Bruna

In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense that the values of all local minima are no worse than the…

Machine Learning · Statistics 2019-07-10 Kenji Kawaguchi , Yoshua Bengio

Due to the success of deep learning to solving a variety of challenging machine learning tasks, there is a rising interest in understanding loss functions for training neural networks from a theoretical aspect. Particularly, the properties…

Machine Learning · Statistics 2017-11-01 Yi Zhou , Yingbin Liang

This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances…

Machine Learning · Computer Science 2019-01-03 Zheng-Chu Guo , Lei Shi , Shao-Bo Lin

In this paper we study the problem of learning a shallow artificial neural network that best fits a training data set. We study this problem in the over-parameterized regime where the number of observations are fewer than the number of…

Machine Learning · Computer Science 2022-08-25 Mahdi Soltanolkotabi , Adel Javanmard , Jason D. Lee

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

Machine Learning · Computer Science 2020-08-11 Rotem Mulayoff , Tomer Michaeli

Sparse neural networks have received increasing interest due to their small size compared to dense networks. Nevertheless, most existing works on neural network theory have focused on dense neural networks, and the understanding of sparse…

Machine Learning · Computer Science 2022-05-18 Dachao Lin , Ruoyu Sun , Zhihua Zhang

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of…

Machine Learning · Computer Science 2023-11-14 Erik Lien Bolager , Iryna Burak , Chinmay Datar , Qing Sun , Felix Dietrich

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

Neural and Evolutionary Computing · Computer Science 2016-09-23 Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio