English
Related papers

Related papers: Avoiding Spurious Local Minima in Deep Quadratic N…

200 papers

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

In this paper, we analyze the effects of depth and width on the quality of local minima, without strong over-parameterization and simplification assumptions in the literature. Without any simplification assumption, for deep nonlinear neural…

Machine Learning · Computer Science 2019-07-10 Kenji Kawaguchi , Jiaoyang Huang , Leslie Pack Kaelbling

Modern neural networks are often quite wide, causing large memory and computation costs. It is thus of great interest to train a narrower network. However, training narrow neural nets remains a challenging task. We ask two theoretical…

Machine Learning · Computer Science 2022-10-24 Jiawei Zhang , Yushun Zhang , Mingyi Hong , Ruoyu Sun , Zhi-Quan Luo

Deep learning has achieved many breakthroughs in modern classification tasks. Numerous architectures have been proposed for different data structures but when it comes to the loss function, the cross-entropy loss is the predominant choice.…

Machine Learning · Statistics 2021-12-08 Tianyang Hu , Jun Wang , Wenjia Wang , Zhenguo Li

In this paper we develop a new framework that captures the common landscape underlying the common non-convex low-rank matrix problems including matrix sensing, matrix completion and robust PCA. In particular, we show for all above problems…

Machine Learning · Computer Science 2017-04-04 Rong Ge , Chi Jin , Yi Zheng

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

Machine Learning · Computer Science 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai

In this paper, we propose a geometric framework to analyze the convergence properties of gradient descent trajectories in the context of linear neural networks. We translate a well-known empirical observation of linear neural nets into a…

Machine Learning · Computer Science 2023-08-02 Yacine Chitour , Zhenyu Liao , Romain Couillet

Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance.…

Machine Learning · Computer Science 2021-09-14 Mitchell Wortsman , Maxwell Horton , Carlos Guestrin , Ali Farhadi , Mohammad Rastegari

We focus on semiparametric regression that has played a central role in statistics, and exploit the powerful learning ability of deep neural networks (DNNs) while enabling statistical inference on parameters of interest that offers…

Statistics Theory · Mathematics 2025-04-29 Shunxing Yan , Ziyuan Chen , Fang Yao

Random pruning is arguably the most naive way to attain sparsity in neural networks, but has been deemed uncompetitive by either post-training pruning or sparse training. In this paper, we focus on sparse training and highlight a perhaps…

Machine Learning · Computer Science 2022-02-08 Shiwei Liu , Tianlong Chen , Xiaohan Chen , Li Shen , Decebal Constantin Mocanu , Zhangyang Wang , Mykola Pechenizkiy

In this paper, we theoretically prove that the deep ReLU neural networks do not lie in spurious local minima in the loss landscape under the Neural Tangent Kernel (NTK) regime, that is, in the gradient descent training dynamics of the deep…

Machine Learning · Statistics 2022-05-20 Tohru Nitta

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Distributed training in deep learning (DL) is common practice as data and models grow. The current practice for distributed training of deep neural networks faces the challenges of communication bottlenecks when operating at scale, and…

Machine Learning · Computer Science 2020-12-21 Shubhankar Gahlot , Junqi Yin , Mallikarjun Shankar

Due to the non-convex nature of training Deep Neural Network (DNN) models, their effectiveness relies on the use of non-convex optimization heuristics. Traditional methods for training DNNs often require costly empirical methods to produce…

Machine Learning · Computer Science 2023-12-21 Tolga Ergen , Mert Pilanci

The success of deep learning has revealed the application potential of neural networks across the sciences and opened up fundamental theoretical problems. In particular, the fact that learning algorithms based on simple variants of gradient…

Disordered Systems and Neural Networks · Physics 2022-02-15 Carlo Baldassi , Clarissa Lauditi , Enrico M. Malatesta , Gabriele Perugini , Riccardo Zecchina

The high computational complexity and increasing parameter counts of deep neural networks pose significant challenges for deployment in resource-constrained environments, such as edge devices or real-time systems. To address this, we…

Machine Learning · Computer Science 2025-06-17 Laura Erb , Tommaso Boccato , Alexandru Vasilache , Juergen Becker , Nicola Toschi

Understanding the relation between deep and shallow neural networks is extremely important for the theoretical study of deep learning. In this work, we discover an embedding principle in depth that loss landscape of an NN "contains" all…

Machine Learning · Computer Science 2025-04-15 Zhiwei Bai , Tao Luo , Zhi-Qin John Xu , Yaoyu Zhang

We consider the problem of learning a one-hidden-layer neural network with non-overlapping convolutional layer and ReLU activation, i.e., $f(\mathbf{Z}, \mathbf{w}, \mathbf{a}) = \sum_j a_j\sigma(\mathbf{w}^T\mathbf{Z}_j)$, in which both…

Machine Learning · Computer Science 2018-06-18 Simon S. Du , Jason D. Lee , Yuandong Tian , Barnabas Poczos , Aarti Singh

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

Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…

Machine Learning · Computer Science 2018-12-27 Samet Oymak , Mahdi Soltanolkotabi