English
Related papers

Related papers: Learning Deep Models: Critical Points and Local Op…

200 papers

By using the viewpoint of modern computational algebraic geometry, we explore properties of the optimization landscapes of the deep linear neural network models. After clarifying on the various definitions of "flat" minima, we show that the…

Machine Learning · Statistics 2018-10-19 Dhagash Mehta , Tianran Chen , Tingting Tang , Jonathan D. Hauenstein

Equivariant neural networks have proven to be effective for tasks with known underlying symmetries. However, optimizing equivariant networks can be tricky and best training practices are less established than for standard networks. In…

Machine Learning · Computer Science 2025-11-04 YuQing Xie , Tess Smidt

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

Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima.…

Machine Learning · Computer Science 2016-02-25 Zachary C. Lipton

Relieving the reliance of neural network training on a global back-propagation (BP) has emerged as a notable research topic due to the biological implausibility and huge memory consumption caused by BP. Among the existing solutions, local…

Machine Learning · Computer Science 2024-06-11 Yibo Yang , Xiaojie Li , Motasem Alfarra , Hasan Hammoud , Adel Bibi , Philip Torr , Bernard Ghanem

Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We analyze weight-space symmetries in neural networks and show that overparameterization…

Machine Learning · Computer Science 2026-05-11 Kusha Sareen , Mohammad Pedramfar , Sékou-Oumar Kaba , Mehran Shakerinava , Siamak Ravanbakhsh

We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of parameters. Grouping classifiers into equivalence classes, we…

The success of deep learning is due in large part to our ability to solve certain massive non-convex optimization problems with relative ease. Though non-convex optimization is NP-hard, simple algorithms -- often variants of stochastic…

Machine Learning · Computer Science 2023-03-03 Samuel K. Ainsworth , Jonathan Hayase , Siddhartha Srinivasa

Optimization of frame structures is formulated as a~non-convex optimization problem, which is currently solved to local optimality. In this contribution, we investigate four optimization approaches: (i) general non-linear optimization, (ii)…

Optimization and Control · Mathematics 2019-09-17 Marek Tyburec , Jan Zeman , Martin Kružík , Didier Henrion

When searching for global optima of nonconvex unconstrained optimization problems, it is desirable that every local minimum be a global minimum. This property of having no spurious local minima is true in various problems of interest…

Optimization and Control · Mathematics 2023-11-16 Cédric Josz , Xiaopeng Li

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can…

Machine Learning · Statistics 2023-03-03 Florian Graf , Christoph D. Hofer , Marc Niethammer , Roland Kwitt

We propose an implicit neural formulation of optimal transport that eliminates adversarial min--max optimization and multi-network architectures commonly used in existing approaches. Our key idea is to parameterize a single potential in the…

Optimization and Control · Mathematics 2026-05-12 Yesom Park , Eric Gelphman , Stanley Osher , Samy Wu Fung

This paper presents a canonical d.c. (difference of canonical and convex functions) programming problem, which can be used to model general global optimization problems in complex systems. It shows that by using the canonical duality…

Optimization and Control · Mathematics 2016-07-13 Zhong Jin , David Y Gao

The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth. Here we consider the natural `dual' scenario for networks of bounded width and arbitrary depth. Precisely, let $n$ be the number…

Machine Learning · Computer Science 2020-06-09 Patrick Kidger , Terry Lyons

Despite their practical success, a theoretical understanding of the loss landscape of neural networks has proven challenging due to the high-dimensional, non-convex, and highly nonlinear structure of such models. In this paper, we…

Machine Learning · Computer Science 2020-07-21 Abbas Kazemipour , Brett W. Larsen , Shaul Druckmann

Composite minimization is a powerful framework in large-scale convex optimization, based on decoupling of the objective function into terms with structurally different properties and allowing for more flexible algorithmic design. We…

Optimization and Control · Mathematics 2023-02-17 Jelena Diakonikolas , Cristóbal Guzmán

This paper considers the decentralized convex optimization problem, which has a wide range of applications in large-scale machine learning, sensor networks, and control theory. We propose novel algorithms that achieve optimal computation…

Machine Learning · Computer Science 2023-10-11 Haishan Ye , Luo Luo , Ziang Zhou , Tong Zhang

Deep neural networks have shown the ability to extract universal feature representations from data such as images and text that have been useful for a variety of learning tasks. However, the fruits of representation learning have yet to be…

Machine Learning · Computer Science 2023-03-28 Liam Collins , Hamed Hassani , Aryan Mokhtari , Sanjay Shakkottai

We consider optimization problems in which the goal is find a $k$-dimensional subspace of $\mathbb{R}^n$, $k<<n$, which minimizes a convex and smooth loss. Such problems generalize the fundamental task of principal component analysis (PCA)…

Optimization and Control · Mathematics 2022-10-27 Dan Garber , Ron Fisher

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