English
Related papers

Related papers: Geometry-induced Regularization in Deep ReLU Neura…

200 papers

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In this work, we show…

Machine Learning · Computer Science 2015-11-04 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Deep learning is the mainstream technique for many machine learning tasks, including image recognition, machine translation, speech recognition, and so on. It has outperformed conventional methods in various fields and achieved great…

Machine Learning · Computer Science 2018-06-01 Na Lei , Zhongxuan Luo , Shing-Tung Yau , David Xianfeng Gu

Neural network training is usually accomplished by solving a non-convex optimization problem using stochastic gradient descent. Although one optimizes over the networks parameters, the main loss function generally only depends on the…

Machine Learning · Computer Science 2023-02-10 Julius Berner , Dennis Elbrächter , Philipp Grohs

We discovered that the neural networks, especially the deep ReLU networks, demonstrate an `over-generalization' phenomenon. That is, the output values for the inputs that were not seen during training are mapped close to the output range…

Machine Learning · Computer Science 2024-10-23 Harsh Shrivastava

Randomly connected neural networks have long served as a theoretical tool for studying collective dynamics in neural populations, yet quantitative comparisons to experiments remain limited. Recent technological advances have made it…

Neurons and Cognition · Quantitative Biology 2026-05-27 Zehui Zhao , Michael J Pasek , Ilya M Nemenman

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

We develop a geometric approximation theory for deep feed-forward neural networks with ReLU activations. Given a $d$-dimensional hypersurface in $\mathbb{R}^{d+1}$ represented as the graph of a $C^2$-function $\phi$, we show that a deep…

Machine Learning · Computer Science 2024-07-08 Jonatan Vallin , Karl Larsson , Mats G. Larson

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer $l$, the number…

Machine Learning · Computer Science 2020-06-30 Yuandong Tian

We study the optimization landscape and the stability properties of training problems with squared loss for neural networks and general nonlinear conic approximation schemes. It is demonstrated that, if a nonlinear conic approximation…

Optimization and Control · Mathematics 2021-12-03 Constantin Christof

We study the parameterized complexity of training two-layer neural networks with respect to the dimension of the input data and the number of hidden neurons, considering ReLU and linear threshold activation functions. Albeit the…

Computational Complexity · Computer Science 2024-01-19 Vincent Froese , Christoph Hertrich

Deep neural networks learn feature representations via complex geometric transformations of the input data manifold. Despite the models' empirical success across domains, our understanding of neural feature representations is still…

Machine Learning · Computer Science 2025-09-29 Moritz Hehl , Max von Renesse , Melanie Weber

Deep learning relies on good initialization schemes and hyperparameter choices prior to training a neural network. Random weight initializations induce random network ensembles, which give rise to the trainability, training speed, and…

Machine Learning · Statistics 2019-10-25 Rebekka Burkholz , Alina Dubatovka

Neural multivariate regression underpins a wide range of domains, including control, robotics, and finance, yet the geometry of its learned representations remains poorly characterized. While neural collapse has been shown to benefit…

Machine Learning · Computer Science 2026-05-11 George Andriopoulos , Zixuan Dong , Bimarsha Adhikari , Keith Ross

A recent line of research on deep learning focuses on the extremely over-parameterized setting, and shows that when the network width is larger than a high degree polynomial of the training sample size $n$ and the inverse of the target…

Machine Learning · Computer Science 2022-01-03 Zixiang Chen , Yuan Cao , Difan Zou , Quanquan Gu

We study convolutional neural networks with monomial activation functions. Specifically, we prove that their parameterization map is regular and is an isomorphism almost everywhere, up to rescaling the filters. By leveraging on tools from…

Machine Learning · Computer Science 2025-03-04 Vahid Shahverdi , Giovanni Luca Marchetti , Kathlén Kohn

Learning maps between data samples is fundamental. Applications range from representation learning, image translation and generative modeling, to the estimation of spatial deformations. Such maps relate feature vectors, or map between…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Hastings Greer , Roland Kwitt , Francois-Xavier Vialard , Marc Niethammer

For any given neural network architecture a permutation of weights and biases results in the same functional network. This implies that optimization algorithms used to `train' or `learn' the network are faced with a very large number (in…

Optimization and Control · Mathematics 2022-02-22 Harbir Antil , Thomas S. Brown , Rainald Löhner , Fumiya Togashi , Deepanshu Verma

Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to use learning-based methods, where fixed functions or…

Machine Learning · Computer Science 2025-04-09 Anne Gagneux , Mathurin Massias , Emmanuel Soubies , Rémi Gribonval