English
Related papers

Related papers: Spurious Valleys in Two-layer Neural Network Optim…

200 papers

Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness. Most existing function approximation…

Machine Learning · Statistics 2022-06-10 Hao Liu , Minshuo Chen , Siawpeng Er , Wenjing Liao , Tong Zhang , Tuo Zhao

The training of neural networks is a complex, high-dimensional, non-convex and noisy optimization problem whose theoretical understanding is interesting both from an applicative perspective and for fundamental reasons. A core challenge is…

Statistical Mechanics · Physics 2023-04-19 Theo Jules , Gal Brener , Tal Kachman , Noam Levi , Yohai Bar-Sinai

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

Stochastic descent methods (of the gradient and mirror varieties) have become increasingly popular in optimization. In fact, it is now widely recognized that the success of deep learning is not only due to the special deep architecture of…

Machine Learning · Computer Science 2019-01-21 Navid Azizan , Babak Hassibi

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very…

Machine Learning · Computer Science 2016-08-01 Gao Huang , Yu Sun , Zhuang Liu , Daniel Sedra , Kilian Weinberger

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Machine Learning · Computer Science 2026-05-12 Jianfei Li , Shuo Huang , Han Feng , Ding-Xuan Zhou , Gitta Kutyniok

In this paper, we present some theoretical work to explain why simple gradient descent methods are so successful in solving non-convex optimization problems in learning large-scale neural networks (NN). After introducing a mathematical tool…

Machine Learning · Computer Science 2023-05-01 Hui Jiang

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

Many randomized optimization algorithms are rank-invariant, relying solely on the relative ordering of solutions rather than absolute fitness values. We introduce a stronger notion of rank landscape invariance: two problems are equivalent…

Artificial Intelligence · Computer Science 2026-04-08 Arnaud Liefooghe , Sébastien Verel

We consider gradient-based optimisation of wide, shallow neural networks, where the output of each hidden node is scaled by a positive parameter. The scaling parameters are non-identical, differing from the classical Neural Tangent Kernel…

Machine Learning · Statistics 2025-02-19 Francois Caron , Fadhel Ayed , Paul Jung , Hoil Lee , Juho Lee , Hongseok Yang

One of the central questions in the theory of deep learning is to understand how neural networks learn hierarchical features. The ability of deep networks to extract salient features is crucial to both their outstanding generalization…

Machine Learning · Computer Science 2025-04-03 Eshaan Nichani , Alex Damian , Jason D. Lee

Training a classifier under non-convex constraints has gotten increasing attention in the machine learning community thanks to its wide range of applications such as algorithmic fairness and class-imbalanced classification. However, several…

Machine Learning · Statistics 2022-10-31 You-Lin Chen , Zhaoran Wang , Mladen Kolar

Accurate quantification of uncertainty in neural network predictions remains a central challenge for scientific applications involving high-dimensional, correlated data. While existing methods capture either aleatoric or epistemic…

Machine Learning · Computer Science 2025-08-26 Harrison J. Goldwyn , Mitchell Krock , Johann Rudi , Daniel Getter , Julie Bessac

Recent results in the literature suggest that the penultimate (second-to-last) layer representations of neural networks that are trained for classification exhibit a clustering property called neural collapse (NC). We study the implicit…

Machine Learning · Computer Science 2022-09-29 Tomer Galanti , Liane Galanti , Ido Ben-Shaul

The loss landscape of deep neural networks (DNNs) is commonly considered complex and wildly fluctuated. However, an interesting observation is that the loss surfaces plotted along Gaussian noise directions are almost v-basin ones with the…

Machine Learning · Computer Science 2025-06-09 Yichu Xu , Xin-Chun Li , Lan Li , De-Chuan Zhan

The paper surveys recent progresses in understanding the dynamics and loss landscape of the gradient flow equations associated to deep linear neural networks, i.e., the gradient descent training dynamics (in the limit when the step size…

Machine Learning · Computer Science 2025-11-14 Joel Wendin , Claudio Altafini

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

The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks. Despite various tricks and techniques that have been employed to alleviate the problem in practice,…

Machine Learning · Computer Science 2021-12-06 Yao Lu , Stephen Gould , Thalaiyasingam Ajanthan

Stochastic gradient descent (SGD) is widely used in deep learning due to its computational efficiency, but a complete understanding of why SGD performs so well remains a major challenge. It has been observed empirically that most…

Machine Learning · Statistics 2022-06-20 Carmina Fjellström , Kaj Nyström

Deep learning, in the form of artificial neural networks, has achieved remarkable practical success in recent years, for a variety of difficult machine learning applications. However, a theoretical explanation for this remains a major open…

Machine Learning · Computer Science 2016-06-15 Itay Safran , Ohad Shamir