English
Related papers

Related papers: Understanding Mode Connectivity via Parameter Spac…

200 papers

Linear Mode Connectivity (LMC) refers to the phenomenon that performance remains consistent for linearly interpolated models in the parameter space. For independently optimized model pairs from different random initializations, achieving…

Machine Learning · Computer Science 2025-02-17 Ryuichi Kanoh , Mahito Sugiyama

Using a generalized random recurrent neural network model, and by extending our recently developed mean-field approach [J. Aljadeff, M. Stern, T. Sharpee, Phys. Rev. Lett. 114, 088101 (2015)], we study the relationship between the network…

Disordered Systems and Neural Networks · Physics 2016-02-09 Johnatan Aljadeff , David Renfrew , Marina Vegué , Tatyana O. Sharpee

In this note we prove that minimal networks enjoy minimizing properties for the length functional. A minimal network is, roughly speaking, a subset of $\mathbb{R}^2$ composed of straight segments joining at triple junctions forming angles…

Optimization and Control · Mathematics 2023-08-30 Alessandra Pluda , Marco Pozzetta

In a first step towards the comprehension of neural activity, one should focus on the stability of the various dynamical states. Even the characterization of idealized regimes, such as a perfectly periodic spiking activity, reveals…

Disordered Systems and Neural Networks · Physics 2014-09-08 Simona Olmi , Antonio Politi , Alessandro Torcini

We present a study on connection errors in networks of linear features and methods of error detection. We model networks with special connection specifications as networks with hierarchically connected features and define errors considering…

Data Structures and Algorithms · Computer Science 2015-04-07 Panteleimon Rodis

Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications. Experimental results suggest that sufficiently deep and wide neural networks are not…

Machine Learning · Computer Science 2020-09-01 Henning Petzka , Cristian Sminchisescu

A common approach to modeling networks assigns each node to a position on a low-dimensional manifold where distance is inversely proportional to connection likelihood. More positive manifold curvature encourages more and tighter…

Methodology · Statistics 2023-01-03 Shane Lubold , Arun G. Chandrasekhar , Tyler H. McCormick

The residual network is now one of the most effective structures in deep learning, which utilizes the skip connections to ``guarantee" the performance will not get worse. However, the non-convexity of the neural network makes it unclear…

Machine Learning · Computer Science 2020-06-11 Lifu Wang , Bo Shen , Ning Zhao , Zhiyuan Zhang

Physical and functional constraints on biological networks lead to complex topological patterns across multiple scales in their organization. A particular type of higher-order network feature that has received considerable interest is…

Quantitative Methods · Quantitative Biology 2024-10-15 Alexis Bénichou , Jean-Baptiste Masson , Christian L. Vestergaard

We present a new, novel approach to obtaining a network's connectivity. More specifically, we show that there exists a relationship between a network's graph isoperimetric properties and its conditional connectivity. A network's…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-07-27 Qiang Zhu , Fang Ma , Guodong Guo , Dajin Wang , Weisheng Chen

Empirical studies have shown that continuous low-loss paths can be constructed between independently trained neural network models. This phenomenon, known as mode connectivity, refers to the existence of such paths between distinct…

Machine Learning · Computer Science 2026-05-29 Yongding Tian , Zaid Al-Ars , Maksim Kitsak , Peter Hofstee

Functional connectivity is a fundamental property of neural networks that quantifies the segregation and integration of information between cortical areas. Due to mathematical complexity, a theory that could explain how the parameters of…

Neurons and Cognition · Quantitative Biology 2016-05-27 Diego Fasoli , Anna Cattani , Stefano Panzeri

Human brain connectome studies aim at extracting and analyzing relevant features associated to pathologies of interest. Usually this consists in modeling the brain connectome as a graph and in using graph metrics as features. A fine brain…

Neurons and Cognition · Quantitative Biology 2020-05-04 Félix Renard , Christian Heinrich , Marine Bouthillon , Maleka Schenck , Francis Schneider , Stéphane Kremer , Sophie Achard

Centrality metrics have been widely applied to identify the nodes in a graph whose removal is effective in decomposing the graph into smaller sub-components. The node--removal process is generally used to test network robustness against…

Social and Information Networks · Computer Science 2022-04-25 Lucia Cavallaro , Stefania Costantini , Pasquale De Meo , Antonio Liotta , Giovanni Stilo

Skip connections made the training of very deep networks possible and have become an indispensable component in a variety of neural architectures. A completely satisfactory explanation for their success remains elusive. Here, we present a…

Neural and Evolutionary Computing · Computer Science 2018-03-06 A. Emin Orhan , Xaq Pitkow

The comprehension of the mechanisms at the basis of the functioning of complexly interconnected networks represents one of the main goals of neuroscience. In this work, we investigate how the structure of recurrent connectivity influences…

Disordered Systems and Neural Networks · Physics 2019-05-14 Sungmin Hwang , Viola Folli , Enrico Lanza , Giorgio Parisi , Giancarlo Ruocco , Francesco Zamponi

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

Networks are useful for describing systems of interacting objects, where the nodes represent the objects and the edges represent the interactions between them. The applications include chemical and metabolic systems, food webs as well as…

Computational Physics · Physics 2009-10-20 Baruch Barzel , Ofer Biham

We argue that in fully-connected networks a phase transition delimits the over- and under-parametrized regimes where fitting can or cannot be achieved. Under some general conditions, we show that this transition is sharp for the hinge loss.…

Machine Learning · Computer Science 2020-01-08 Stefano Spigler , Mario Geiger , Stéphane d'Ascoli , Levent Sagun , Giulio Biroli , Matthieu Wyart

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