English
Related papers

Related papers: Stuck in a What? Adventures in Weight Space

200 papers

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 show that deep neural networks trained across diverse tasks exhibit remarkably similar low-dimensional parametric subspaces. We provide the first large-scale empirical evidence that demonstrates that neural networks systematically…

Machine Learning · Computer Science 2025-12-09 Prakhar Kaushik , Shravan Chaudhari , Ankit Vaidya , Rama Chellappa , Alan Yuille

We study the geometry of linear networks with one-dimensional convolutional layers. The function spaces of these networks can be identified with semi-algebraic families of polynomials admitting sparse factorizations. We analyze the impact…

Machine Learning · Computer Science 2024-01-29 Kathlén Kohn , Guido Montúfar , Vahid Shahverdi , Matthew Trager

It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is…

Machine Learning · Computer Science 2020-08-11 Rotem Mulayoff , Tomer Michaeli

Convolutional neural networks are widely used in imaging and image recognition. Learning such networks from training data leads to the minimization of a non-convex function. This makes the analysis of standard optimization methods such as…

Optimization and Control · Mathematics 2026-01-14 Jona-Maria Diederen , Holger Rauhut , Ulrich Terstiege

Predictions made by deep neural networks were shown to be highly sensitive to small changes made in the input space where such maliciously crafted data points containing small perturbations are being referred to as adversarial examples. On…

Machine Learning · Computer Science 2022-06-01 Utku Ozbulak , Manvel Gasparyan , Shodhan Rao , Wesley De Neve , Arnout Van Messem

We consider neural networks with a single hidden layer and non-decreasing homogeneous activa-tion functions like the rectified linear units. By letting the number of hidden units grow unbounded and using classical non-Euclidean…

Machine Learning · Computer Science 2016-11-01 Francis Bach

The permutation symmetry of neurons in each layer of a deep neural network gives rise not only to multiple equivalent global minima of the loss function, but also to first-order saddle points located on the path between the global minima.…

Machine Learning · Computer Science 2019-07-08 Johanni Brea , Berfin Simsek , Bernd Illing , Wulfram Gerstner

Nonlinear embedding manifold learning methods provide invaluable visual insights into the structure of high-dimensional data. However, due to a complicated nonconvex objective function, these methods can easily get stuck in local minima and…

Machine Learning · Computer Science 2019-12-30 Max Vladymyrov

Understanding the structure of loss landscape of deep neural networks (DNNs)is obviously important. In this work, we prove an embedding principle that the loss landscape of a DNN "contains" all the critical points of all the narrower DNNs.…

Machine Learning · Computer Science 2022-01-13 Yaoyu Zhang , Zhongwang Zhang , Tao Luo , Zhi-Qin John Xu

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

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

The loss landscapes of neural networks contain minima and saddle points that may be connected in flat regions or appear in isolation. We identify and characterize a special structure in the loss landscape: channels along which the loss…

Machine Learning · Computer Science 2026-05-11 Flavio Martinelli , Alexander Van Meegen , Berfin Şimşek , Wulfram Gerstner , Johanni Brea

We theoretically study the landscape of the training error for neural networks in overparameterized cases. We consider three basic methods for embedding a network into a wider one with more hidden units, and discuss whether a minimum point…

Machine Learning · Computer Science 2019-06-17 Kenji Fukumizu , Shoichiro Yamaguchi , Yoh-ichi Mototake , Mirai Tanaka

The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…

Machine Learning · Computer Science 2022-04-27 Thien Le , Stefanie Jegelka

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

Recently, interesting empirical phenomena known as Neural Collapse have been observed during the final phase of training deep neural networks for classification tasks. We examine this issue when the feature dimension d is equal to the…

Machine Learning · Computer Science 2024-07-23 Yi Shen , Shao Gu

Sharpness-aware minimization (SAM) is a recently proposed training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains. Instead of minimizing the loss of the current…

Machine Learning · Computer Science 2023-01-18 Hoki Kim , Jinseong Park , Yujin Choi , Jaewook Lee

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

Machine Learning · Computer Science 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

Generalization analyses of deep learning typically assume that the training converges to a fixed point. But, recent results indicate that in practice, the weights of deep neural networks optimized with stochastic gradient descent often…

Machine Learning · Computer Science 2022-08-22 Nisha Chandramoorthy , Andreas Loukas , Khashayar Gatmiry , Stefanie Jegelka