English
Related papers

Related papers: Depth Creates No Bad Local Minima

200 papers

Deep neural network is a state-of-art method in modern science and technology. Much statistical literature have been devoted to understanding its performance in nonparametric estimation, whereas the results are suboptimal due to a redundant…

Machine Learning · Computer Science 2021-08-18 Ruiqi Liu , Ben Boukai , Zuofeng Shang

The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show…

Machine Learning · Computer Science 2016-10-31 Antoine Gautier , Quynh Nguyen , Matthias Hein

The existence of local minima for one-hidden-layer ReLU networks has been investigated theoretically in [8]. Based on the theory, in this paper, we first analyze how big the probability of existing local minima is for 1D Gaussian data and…

Machine Learning · Computer Science 2020-06-17 Bo Liu

We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and diversity of non-strict…

Statistics Theory · Mathematics 2024-09-26 El Mehdi Achour , François Malgouyres , Sébastien Gerchinovitz

We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets.…

Machine Learning · Computer Science 2021-12-28 Nicholas P Baskerville , Diego Granziol , Jonathan P Keating

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

Conventional wisdom states that deep linear neural networks benefit from expressiveness and optimization advantages over a single linear layer. This paper suggests that, in practice, the training process of deep linear fully-connected…

Machine Learning · Computer Science 2022-06-10 Oriel BenShmuel

The critical locus of the loss function of a neural network is determined by the geometry of the functional space and by the parameterization of this space by the network's weights. We introduce a natural distinction between pure critical…

Machine Learning · Computer Science 2020-04-06 Matthew Trager , Kathlén Kohn , Joan Bruna

Training neural networks involves finding minima of a high-dimensional non-convex loss function. Knowledge of the structure of this energy landscape is sparse. Relaxing from linear interpolations, we construct continuous paths between…

Machine Learning · Statistics 2019-02-25 Felix Draxler , Kambis Veschgini , Manfred Salmhofer , Fred A. Hamprecht

Depth estimation is of critical interest for scene understanding and accurate 3D reconstruction. Most recent approaches in depth estimation with deep learning exploit geometrical structures of standard sharp images to predict corresponding…

Computer Vision and Pattern Recognition · Computer Science 2018-09-07 Marcela Carvalho , Bertrand Le Saux , Pauline Trouvé-Peloux , Andrés Almansa , Frédéric Champagnat

Techniques involving factorization are found in a wide range of applications and have enjoyed significant empirical success in many fields. However, common to a vast majority of these problems is the significant disadvantage that the…

Numerical Analysis · Computer Science 2015-06-26 Benjamin D. Haeffele , Rene Vidal

We introduce a principled approach for unsupervised structure learning of deep neural networks. We propose a new interpretation for depth and inter-layer connectivity where conditional independencies in the input distribution are encoded…

Machine Learning · Statistics 2018-10-18 Raanan Y. Rohekar , Shami Nisimov , Yaniv Gurwicz , Guy Koren , Gal Novik

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

In the recent literature the important role of depth in deep learning has been emphasized. In this paper we argue that sufficient width of a feedforward network is equally important by answering the simple question under which conditions…

Machine Learning · Computer Science 2018-06-11 Quynh Nguyen , Mahesh Chandra Mukkamala , Matthias Hein

Neural networks have been very successful in many applications; we often, however, lack a theoretical understanding of what the neural networks are actually learning. This problem emerges when trying to generalise to new data sets. The…

Classical Analysis and ODEs · Mathematics 2022-11-22 Matthew Thorpe , Yves van Gennip

The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to understand their optimization dynamics. In this paper, we study the sharpness of deep linear networks for univariate regression. Minimizers can…

Machine Learning · Statistics 2024-10-29 Pierre Marion , Lénaïc Chizat

Linear networks provide valuable insights into the workings of neural networks in general. This paper identifies conditions under which the gradient flow provably trains a linear network, in spite of the non-strict saddle points present in…

Optimization and Control · Mathematics 2020-06-30 Armin Eftekhari

The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear…

Machine Learning · Statistics 2017-10-23 Yi Zhou , Yingbin Liang

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos
‹ Prev 1 3 4 5 6 7 10 Next ›