English
Related papers

Related papers: Interpretable global minima of deep ReLU neural ne…

200 papers

For fixed training data and network parameters in the other layers the L1 loss of a ReLU neural network as a function of the first layer's parameters is a piece-wise affine function. We use the Deep ReLU Simplex algorithm to iteratively…

Machine Learning · Statistics 2021-05-07 Peter Hinz

We study finite sample expressivity, i.e., memorization power of ReLU networks. Recent results require $N$ hidden nodes to memorize/interpolate arbitrary $N$ data points. In contrast, by exploiting depth, we show that 3-layer ReLU networks…

Machine Learning · Computer Science 2019-10-30 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

While neural networks are used for classification tasks across domains, a long-standing open problem in machine learning is determining whether neural networks trained using standard procedures are optimal for classification, i.e., whether…

Machine Learning · Computer Science 2023-05-03 Adityanarayanan Radhakrishnan , Mikhail Belkin , Caroline Uhler

We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting…

Machine Learning · Computer Science 2019-05-21 Jens Behrmann , Will Grathwohl , Ricky T. Q. Chen , David Duvenaud , Jörn-Henrik Jacobsen

We consider the optimization problem associated with training two-layer ReLU networks with \(d\) inputs under the squared loss, where the labels are generated by a target network. Recent work has identified two distinct classes of infinite…

Machine Learning · Computer Science 2026-01-21 Yossi Arjevani

Viewing neural network models in terms of their loss landscapes has a long history in the statistical mechanics approach to learning, and in recent years it has received attention within machine learning proper. Among other things, local…

Machine Learning · Computer Science 2021-12-14 Yaoqing Yang , Liam Hodgkinson , Ryan Theisen , Joe Zou , Joseph E. Gonzalez , Kannan Ramchandran , Michael W. Mahoney

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

Machine Learning · Computer Science 2018-06-19 Utku Evci

We consider the computational complexity of training depth-2 neural networks composed of rectified linear units (ReLUs). We show that, even for the case of a single ReLU, finding a set of weights that minimizes the squared error (even…

Computational Complexity · Computer Science 2018-10-17 Pasin Manurangsi , Daniel Reichman

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

Understanding the classifications of deep neural networks, e.g. used in safety-critical situations, is becoming increasingly important. While recent models can locally explain a single decision, to provide a faithful global explanation…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Thomas Norrenbrock , Timo Kaiser , Sovan Biswas , Ramesh Manuvinakurike , Bodo Rosenhahn

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep…

Machine Learning · Statistics 2023-03-30 Chang hoon Song , Geonho Hwang , Jun ho Lee , Myungjoo Kang

While metric and similarity learning has been extensively studied from several theoretical perspectives, a rigorous understanding of its generalization performance is still lacking. In this paper, we investigate the generalization behavior…

Machine Learning · Statistics 2026-05-19 Junyu Zhou , Puyu Wang , Ding-Xuan Zhou

The modern strategy for training deep neural networks for classification tasks includes optimizing the network's weights even after the training error vanishes to further push the training loss toward zero. Recently, a phenomenon termed…

Machine Learning · Computer Science 2022-10-13 Tom Tirer , Joan Bruna

We consider the approximation of functions by 2-layer neural networks with a small number of hidden weights based on the squared loss and small datasets. Due to the highly non-convex energy landscape, gradient-based training often suffers…

Machine Learning · Computer Science 2025-08-14 Johannes Hertrich , Sebastian Neumayer

Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximations. However, they are also known for their limited modeling…

Machine Learning · Statistics 2016-11-22 Qinliang Su , Xuejun Liao , Chunyuan Li , Zhe Gan , Lawrence Carin

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise…

Machine Learning · Computer Science 2023-10-03 Dmitry Chistikov , Matthias Englert , Ranko Lazic

We study dropout in two-layer neural networks with rectified linear unit (ReLU) activations. Under mild overparametrization and assuming that the limiting kernel can separate the data distribution with a positive margin, we show that…

Machine Learning · Computer Science 2020-10-27 Poorya Mianjy , Raman Arora

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

The foundations of deep learning are supported by the seemingly opposing perspectives of approximation or learning theory. The former advocates for large/expressive models that need not generalize, while the latter considers classes that…

Machine Learning · Computer Science 2025-06-27 Ruiyang Hong , Anastasis Kratsios

ReLU neural networks trained as surrogate models can be embedded exactly in mixed-integer linear programs (MILPs), enabling global optimization over the learned function. The tractability of the resulting MILP depends on structural…

Optimization and Control · Mathematics 2026-04-27 Calvin Tsay
‹ Prev 1 3 4 5 6 7 10 Next ›