中文
相关论文

相关论文: The star-shaped space of solutions of the spherica…

200 篇论文

One of the most intriguing findings in the structure of neural network landscape is the phenomenon of mode connectivity: For two typical global minima, there exists a path connecting them without barrier. This concept of mode connectivity…

机器学习 · 计算机科学 2024-04-10 Zhanran Lin , Puheng Li , Lei Wu

We study the binary and continuous negative-margin perceptrons as simple non-convex neural network models learning random rules and associations. We analyze the geometry of the landscape of solutions in both models and find important…

无序系统与神经网络 · 物理学 2023-07-25 Carlo Baldassi , Enrico M. Malatesta , Gabriele Perugini , Riccardo Zecchina

Neural computation in biological and artificial networks relies on the nonlinear summation of many inputs. The structural connectivity matrix of synaptic weights between neurons is a critical determinant of overall network function, but…

神经元与认知 · 定量生物学 2022-07-01 Tirthabir Biswas , James E. Fitzgerald

In these pedagogic notes I review the statistical mechanics approach to neural networks, focusing on the paradigmatic example of the perceptron architecture with binary an continuous weights, in the classification setting. I will review the…

无序系统与神经网络 · 物理学 2025-02-20 Enrico M. Malatesta

It has recently been conjectured that neural network solution sets reachable via stochastic gradient descent (SGD) are convex, considering permutation invariances (Entezari et al., 2022). This means that a linear path can connect two…

机器学习 · 计算机科学 2024-06-11 Ankit Sonthalia , Alexander Rubinstein , Ehsan Abbasnejad , Seong Joon Oh

The loss surface of deep neural networks has recently attracted interest in the optimization and machine learning communities as a prime example of high-dimensional non-convex problem. Some insights were recently gained using spin glass…

机器学习 · 统计学 2017-06-05 C. Daniel Freeman , Joan Bruna

Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constraints. In our paper, we show that a key bottleneck in compositional reasoning is not…

The difficulty in exploring potential energy surfaces, which are nonconvex, stems from the presence of many local minima, typically separated by high barriers and often disconnected in configurational space. We obtain the global minimum on…

其他凝聚态物理 · 物理学 2007-05-23 Martin Burke , Sophia N. Yaliraki

We study numerically the cluster structure of random ensembles of two NP-hard optimization problems originating in computational complexity, the vertex-cover problem and the number partitioning problem. We use branch-and-bound type…

无序系统与神经网络 · 物理学 2009-11-13 Alexander K. Hartmann , Alexander Mann , Wolfgang Radenbach

We develop a statistical mechanical approach based on the replica method to study the design space of deep and wide neural networks constrained to meet a large number of training data. Specifically, we analyze the configuration space of the…

无序系统与神经网络 · 物理学 2020-04-17 Hajime Yoshino

Network connectivity is usually addressed for convex domains where a direct line of sight exists between any two transmitting/receiving nodes. Here, we develop a general theory for the network connectivity properties across a small opening,…

无序系统与神经网络 · 物理学 2013-12-13 Orestis Georgiou , Carl P. Dettmann , Justin Coon

The clear understanding of the non-convex landscape of neural network is a complex incomplete problem. This paper studies the landscape of linear (residual) network, the simplified version of the nonlinear network. By treating the gradient…

代数几何 · 数学 2021-02-09 Xiuyi Yang

Statistical-physics calculations in machine learning and theoretical neuroscience often involve lengthy derivations that obscure physical interpretation. Here, we give concise, non-replica derivations of several key results and highlight…

无序系统与神经网络 · 物理学 2025-10-29 David G. Clark , Haim Sompolinsky

The functional features of spatial networks depend upon a non-trivial relationship between the topological and physical structure. Here, we explore that relationship for spatial networks with radial symmetry and disordered fractal…

材料科学 · 物理学 2023-11-01 A. C. Flores-Ortega , J. R. Nicolás-Carlock , J. L. Carrillo-Estrada

In this paper, we investigate the geometric structure of activation spaces of fully connected layers in neural networks and then show applications of this study. We propose an efficient approximation algorithm to characterize the convex…

机器学习 · 计算机科学 2019-04-03 Yuting Jia , Haiwen Wang , Shuo Shao , Huan Long , Yunsong Zhou , Xinbing Wang

Energy-minimizing constraint maps are a natural extension of the obstacle problem within a vectorial framework. Due to inherent topological constraints, these maps manifest a diverse structure that includes singularities similar to harmonic…

偏微分方程分析 · 数学 2024-08-01 Alessio Figalli , André Guerra , Sunghan Kim , Henrik Shahgholian

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…

统计力学 · 物理学 2023-04-19 Theo Jules , Gal Brener , Tal Kachman , Noam Levi , Yohai Bar-Sinai

The study of random landscapes has long relied on counting stationary points: metastable states and the barriers between them. However, this method is useless for describing flat regions, common in constraint satisfaction problems. We…

无序系统与神经网络 · 物理学 2026-02-16 Jaron Kent-Dobias

We propose a dynamical neural network model with a hierarchical and modular structure. The network architecture can be derived by minimizing an energy function that is originally designed based on two kinds of neurons with quite different…

神经元与认知 · 定量生物学 2026-04-14 Kazuyoshi Tsutsumi , Ernst Niebur

Distributing points on a (possibly high-dimensional) sphere with minimal energy is a long-standing problem in and outside the field of mathematics. This paper considers a novel energy function that arises naturally from statistics and…

组合数学 · 数学 2022-03-21 Weibo Fu , Guanyang Wang , Jun Yan
‹ 上一页 1 2 3 10 下一页 ›