English
Related papers

Related papers: On Connected Sublevel Sets in Deep Learning

200 papers

In this paper, we theoretically prove that adding one special neuron per output unit eliminates all suboptimal local minima of any deep neural network, for multi-class classification, binary classification, and regression with an arbitrary…

Machine Learning · Computer Science 2020-01-17 Kenji Kawaguchi , Leslie Pack Kaelbling

We study the complexity of functions computable by deep feedforward neural networks with piecewise linear activations in terms of the symmetries and the number of linear regions that they have. Deep networks are able to sequentially map…

Machine Learning · Statistics 2014-06-10 Guido Montúfar , Razvan Pascanu , Kyunghyun Cho , Yoshua Bengio

A network supporting deep unsupervised learning is presented. The network is an autoencoder with lateral shortcut connections from the encoder to decoder at each level of the hierarchy. The lateral shortcut connections allow the higher…

Machine Learning · Statistics 2015-02-03 Harri Valpola

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a…

Optimization and Control · Mathematics 2025-09-24 Po Chen , Rujun Jiang , Peng Wang

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Sobolev loss is used when training a network to approximate the values and derivatives of a target function at a prescribed set of input points. Recent works have demonstrated its successful applications in various tasks such as…

Machine Learning · Computer Science 2020-08-18 Jorio Cocola , Paul Hand

We study the properties of alignment, a form of implicit regularization, in linear neural networks under gradient descent. We define alignment for fully connected networks with multidimensional outputs and show that it is a natural…

Machine Learning · Computer Science 2020-06-18 Adityanarayanan Radhakrishnan , Eshaan Nichani , Daniel Bernstein , Caroline Uhler

The optimization of multilayer neural networks typically leads to a solution with zero training error, yet the landscape can exhibit spurious local minima and the minima can be disconnected. In this paper, we shed light on this phenomenon:…

Machine Learning · Computer Science 2020-07-24 Alexander Shevchenko , Marco Mondelli

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures. Its prediction rule is provided implicitly based on the…

Machine Learning · Computer Science 2022-02-21 Tianxiang Gao , Hailiang Liu , Jia Liu , Hridesh Rajan , Hongyang Gao

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

We show that for neural network functions that have width less or equal to the input dimension all connected components of decision regions are unbounded. The result holds for continuous and strictly monotonic activation functions as well…

Machine Learning · Computer Science 2021-03-04 Hans-Peter Beise , Steve Dias Da Cruz , Udo Schröder

Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima.…

Machine Learning · Computer Science 2016-02-25 Zachary C. Lipton

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

While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empirical performance. Among them, which one is the best to use is…

Machine Learning · Computer Science 2022-10-11 Jinxin Zhou , Chong You , Xiao Li , Kangning Liu , Sheng Liu , Qing Qu , Zhihui Zhu

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

We prove that training neural networks on 1-D data is equivalent to solving convex Lasso problems with discrete, explicitly defined dictionary matrices. We consider neural networks with piecewise linear activations and depths ranging from 2…

Machine Learning · Computer Science 2024-07-25 Emi Zeger , Yifei Wang , Aaron Mishkin , Tolga Ergen , Emmanuel Candès , Mert Pilanci

It is widely observed that deep learning models with learned parameters generalize well, even with much more model parameters than the number of training samples. We systematically investigate the underlying reasons why deep neural networks…

Machine Learning · Computer Science 2017-11-29 Lei Wu , Zhanxing Zhu , Weinan E

Determining whether deep neural network (DNN) models can reliably recover target functions at overparameterization is a critical yet complex issue in the theory of deep learning. To advance understanding in this area, we introduce a concept…

Machine Learning · Computer Science 2024-06-27 Yaoyu Zhang , Leyang Zhang , Zhongwang Zhang , Zhiwei Bai

It is frequently observed that overparameterized neural networks generalize well. Regarding such phenomena, existing theoretical work mainly devotes to linear settings or fully-connected neural networks. This paper studies the learning…

Machine Learning · Statistics 2023-08-17 Tian-Yi Zhou , Xiaoming Huo