English
Related papers

Related papers: A Deep Neural Network's Loss Surface Contains Ever…

200 papers

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

Training a neural network requires navigating a high-dimensional, non-convex loss surface to find parameters that minimize this loss. In many ways, it is surprising that optimizers such as stochastic gradient descent and ADAM can reliably…

Machine Learning · Computer Science 2026-02-06 Conor Rowan , Finn Murphy-Blanchard

Deep neural networks progressively transform their inputs across multiple processing layers. What are the geometrical properties of the representations learned by these networks? Here we study the intrinsic dimensionality (ID) of…

Machine Learning · Computer Science 2019-10-29 Alessio Ansuini , Alessandro Laio , Jakob H. Macke , Davide Zoccolan

Understanding the structure of neural network loss surfaces, particularly the emergence of low-loss tunnels, is critical for advancing neural network theory and practice. In this paper, we propose a novel approach to directly embed loss…

Machine Learning · Computer Science 2025-03-06 Daniel Dold , Julius Kobialka , Nicolai Palm , Emanuel Sommer , David Rügamer , Oliver Dürr

Deep neural networks have reshaped modern machine learning by learning powerful latent representations that often align with the manifold hypothesis: high-dimensional data lie on lower-dimensional manifolds. In this paper, we establish a…

Machine Learning · Computer Science 2025-06-09 Nico Pelleriti , Max Zimmer , Elias Wirth , Sebastian Pokutta

Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices. Since the weak expression ability of binary weights and features, their accuracy is usually much lower than that of…

Machine Learning · Computer Science 2019-09-18 Mingzhu Shen , Kai Han , Chunjing Xu , Yunhe Wang

Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn…

Computer Vision and Pattern Recognition · Computer Science 2014-02-20 Christian Szegedy , Wojciech Zaremba , Ilya Sutskever , Joan Bruna , Dumitru Erhan , Ian Goodfellow , Rob Fergus

We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \ge \sqrt{2n}$,…

Machine Learning · Computer Science 2018-06-18 Simon S. Du , Jason D. Lee

Hyperparameters greatly impact models' capabilities; however, modern models are too large for extensive search. Instead, researchers design recipes that train well across scales based on their understanding of the hyperparameters. Despite…

Machine Learning · Computer Science 2025-10-06 Nicholas Lourie , He He , Kyunghyun Cho

Neural implicit representations have emerged as a powerful paradigm for 3D reconstruction. However, despite their success, existing methods fail to capture fine geometric details and thin structures, especially in scenarios where only…

Computer Vision and Pattern Recognition · Computer Science 2025-04-23 Aarya Patel , Hamid Laga , Ojaswa Sharma

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized…

Disordered Systems and Neural Networks · Physics 2024-09-17 Hao Liao , Wei Zhang , Zhanyi Huang , Zexiao Long , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Chi Ho Yeung

This paper concerns the universal approximation property with neural networks in variable Lebesgue spaces. We show that, whenever the exponent function of the space is bounded, every function can be approximated with shallow neural networks…

Functional Analysis · Mathematics 2020-07-09 Ángela Capel , Jesús Ocáriz

Under mild assumptions, we investigate the geometry of the loss landscape for two-layer neural networks in the vicinity of global minima. Utilizing novel techniques, we demonstrate: (i) how global minima with zero generalization error…

Machine Learning · Computer Science 2025-04-11 Leyang Zhang , Yaoyu Zhang , Tao Luo

Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, explaining why this is the case is still an open area of…

Machine Learning · Computer Science 2017-11-15 Laurent Dinh , Razvan Pascanu , Samy Bengio , Yoshua Bengio

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world…

Machine Learning · Computer Science 2019-09-27 Hong Liu , Mingsheng Long , Jianmin Wang , Michael I. Jordan

The large spatial/frequency scale of hyperspectral and airborne magnetic and gravitational data causes memory issues when using convolutional neural networks for (sub-) surface characterization. Recently developed fully reversible networks…

Geophysics · Physics 2020-03-18 Bas Peters , Eldad Haber , Keegan Lensink

The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear…

Machine Learning · Statistics 2017-10-23 Yi Zhou , Yingbin Liang

It has been argued in the past that high-dimensional neural networks do not exhibit local minima capable of trapping an optimisation algorithm. However, the relationship between loss surface modality and the neural architecture parameters,…

Machine Learning · Computer Science 2020-01-31 Anna Sergeevna Bosman , Andries Engelbrecht , Mardé Helbig

Datasets such as images, text, or movies are embedded in high-dimensional spaces. However, in important cases such as images of objects, the statistical structure in the data constrains samples to a manifold of dramatically lower…

Machine Learning · Computer Science 2019-10-29 Stefano Recanatesi , Matthew Farrell , Madhu Advani , Timothy Moore , Guillaume Lajoie , Eric Shea-Brown

Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and…

Machine Learning · Computer Science 2018-11-08 Hao Li , Zheng Xu , Gavin Taylor , Christoph Studer , Tom Goldstein