English
Related papers

Related papers: Depth Creates No Bad Local Minima

200 papers

For one-hidden-layer ReLU networks, we prove that all differentiable local minima are global inside differentiable regions. We give the locations and losses of differentiable local minima, and show that these local minima can be isolated…

Machine Learning · Computer Science 2020-06-18 Bo Liu

The loss surface of deep neural networks has recently attracted interest in the optimization and machine learning communities as a prime example of high-dimensional non-convex problem. Some insights were recently gained using spin glass…

Machine Learning · Statistics 2017-06-05 C. Daniel Freeman , Joan Bruna

Compared with avid research activities of deep convolutional neural networks (DCNNs) in practice, the study of theoretical behaviors of DCNNs lags heavily behind. In particular, the universal consistency of DCNNs remains open. In this…

Machine Learning · Computer Science 2021-06-24 Shao-Bo Lin , Kaidong Wang , Yao Wang , Ding-Xuan Zhou

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect…

Machine Learning · Computer Science 2023-02-13 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Volkan Cevher

This paper addresses the problem of estimating the depth map of a scene given a single RGB image. We propose a fully convolutional architecture, encompassing residual learning, to model the ambiguous mapping between monocular images and…

Computer Vision and Pattern Recognition · Computer Science 2016-09-20 Iro Laina , Christian Rupprecht , Vasileios Belagiannis , Federico Tombari , Nassir Navab

Training deep neural networks typically relies on backpropagating high dimensional error signals a computationally intensive process with little evidence supporting its implementation in the brain. However, since most tasks involve…

Machine Learning · Computer Science 2026-01-15 Maher Hanut , Jonathan Kadmon

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem…

Machine Learning · Computer Science 2019-09-10 Mo Zhou , Tianyi Liu , Yan Li , Dachao Lin , Enlu Zhou , Tuo Zhao

We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior classification results in some special cases where the…

Machine Learning · Computer Science 2021-07-20 Vinesha Peiris , Nadezda Sukhorukova , Vera Roshchina

This paper considers several aspects of random matrix universality in deep neural networks. Motivated by recent experimental work, we use universal properties of random matrices related to local statistics to derive practical implications…

The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error. We explain how common variants of the standard NN training procedure change the minimizer obtained. First, we make explicit…

Machine Learning · Statistics 2023-09-26 Manuel Nonnenmacher , David Reeb , Ingo Steinwart

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Deep neural networks have shown incredible performance for inference tasks in a variety of domains. Unfortunately, most current deep networks are enormous cloud-based structures that require significant storage space, which limits scaling…

Information Theory · Computer Science 2020-03-10 Sourya Basu , Lav R. Varshney

We study the benefits of complex-valued weights for neural networks. We prove that shallow complex neural networks with quadratic activations have no spurious local minima. In contrast, shallow real neural networks with quadratic…

Machine Learning · Computer Science 2024-11-13 Xingtu Liu

We demonstrate that a deep neural network can significantly improve optical microscopy, enhancing its spatial resolution over a large field-of-view and depth-of-field. After its training, the only input to this network is an image acquired…

Machine Learning · Computer Science 2017-11-21 Yair Rivenson , Zoltan Gorocs , Harun Gunaydin , Yibo Zhang , Hongda Wang , Aydogan Ozcan

When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to…

Machine Learning · Computer Science 2022-03-15 Jinxin Zhou , Xiao Li , Tianyu Ding , Chong You , Qing Qu , Zhihui Zhu

This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the strong nonconvexity encountered during training deep networks. For cross-entropy models…

Machine Learning · Computer Science 2026-04-28 Yaru Liu , Michael K. Ng , Yiqi Gu

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

Machine Learning · Computer Science 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

Training a very deep neural network is a challenging task, as the deeper a neural network is, the more non-linear it is. We compare the performances of various preconditioned Langevin algorithms with their non-Langevin counterparts for the…

Machine Learning · Computer Science 2023-01-02 Pierre Bras

Machine learning methods are commonly used to solve inverse problems, wherein an unknown signal must be estimated from few indirect measurements generated via a known acquisition procedure. In particular, neural networks perform well…

Machine Learning · Computer Science 2025-12-05 Hannah Laus , Suzanna Parkinson , Vasileios Charisopoulos , Felix Krahmer , Rebecca Willett

Giving provable guarantees for learning neural networks is a core challenge of machine learning theory. Most prior work gives parameter recovery guarantees for one hidden layer networks, however, the networks used in practice have multiple…

Machine Learning · Computer Science 2020-02-21 Surbhi Goel , Rina Panigrahy