English
Related papers

Related papers: Understanding Mode Connectivity via Parameter Spac…

200 papers

In the setting of continual learning, a network is trained on a sequence of tasks, and suffers from catastrophic forgetting. To balance plasticity and stability of network in continual learning, in this paper, we propose a novel network…

Machine Learning · Computer Science 2021-03-18 Shipeng Wang , Xiaorong Li , Jian Sun , Zongben Xu

We consider Convolutional Neural Networks (CNNs) with 2D structured features that are symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships for a sequential recommendation problem, as well as secondary…

Machine Learning · Statistics 2022-03-07 Kehelwala Dewage Gayan Maduranga , Vasily Zadorozhnyy , Qiang Ye

We consider the optimization problem associated with fitting two-layer ReLU networks with respect to the squared loss, where labels are assumed to be generated by a target network. Focusing first on standard Gaussian inputs, we show that…

Machine Learning · Computer Science 2023-12-29 Yossi Arjevani , Michael Field

Connectivity (or equivalently, unweighted maximum flow) is an important measure in graph theory and combinatorial optimization. Given a graph $G$ with vertices $s$ and $t$, the connectivity $\lambda(s,t)$ from $s$ to $t$ is defined to be…

Data Structures and Algorithms · Computer Science 2024-12-25 Shyan Akmal

Topology and nonlinearity are deeply connected. However, whether topological effects can arise solely from the structure of nonlinear interaction terms, and the nature of the resulting topological phases, remain to large extent open…

Quantum Physics · Physics 2026-04-10 Alessandro Coppo , Alexandre Le Boité , Simone Felicetti , Valentina Brosco

Broadcast networks allow one to model networks of identical nodes communicating through message broadcasts. Their parameterized verification aims at proving a property holds for any number of nodes, under any communication topology, and on…

Logic in Computer Science · Computer Science 2023-06-22 Nathalie Bertrand , Patricia Bouyer , Anirban Majumdar

Understanding the dynamics of neural network parameters during training is one of the key challenges in building a theoretical foundation for deep learning. A central obstacle is that the motion of a network in high-dimensional parameter…

Machine Learning · Computer Science 2021-03-30 Daniel Kunin , Javier Sagastuy-Brena , Surya Ganguli , Daniel L. K. Yamins , Hidenori Tanaka

Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex). While it has been observed…

Machine Learning · Computer Science 2024-11-14 Jingtong Su , Ya Shi Zhang , Nikolaos Tsilivis , Julia Kempe

Despite its importance for practical applications, not much is known about the optimal shape of a network that connects in an efficient way a set of points. This problem can be formulated in terms of a multiplex network with a fast layer…

Physics and Society · Physics 2023-11-13 Siddharth Patwardhan , Marc Barthelemy , Sirag Erkol , Santo Fortunato , Filippo Radicchi

The fundamental idea of embedding a network in a metric space is rooted in the principle of proximity preservation. Nodes are mapped into points of the space with pairwise distance that reflects their proximity in the network. Popular…

Physics and Society · Physics 2021-01-15 Yi-Jiao Zhang , Kai-Cheng Yang , Filippo Radicchi

We deal with algorithmic techniques for minimal cost input-connectivity while maintaining controllability of linear systems. The input matrix is assumed to be constrained in the sense that the set of states that each input (if present) can…

Optimization and Control · Mathematics 2019-08-27 Priyanka Dey , Niranjan Balachandran , Debasish Chatterjee

A computational framework is presented for the sampling of the energy surface of magnetic systems via the systematic identification of first-order saddle points that determine connectivity of metastable states and define the mechanisms of…

Materials Science · Physics 2025-12-09 Hendrik Schrautzer , Tim Drevelow , Hannes Jónsson , Pavel F. Bessarab

Permutation of any two hidden units yields invariant properties in typical deep generative neural networks. This permutation symmetry plays an important role in understanding the computation performance of a broad class of neural networks…

Disordered Systems and Neural Networks · Physics 2019-09-17 Tianqi Hou , K. Y. Michael Wong , Haiping Huang

Effective analysis in neuroscience benefits significantly from robust conceptual frameworks. Traditional metrics of interbrain synchrony in social neuroscience typically depend on fixed, correlation-based approaches, restricting their…

Neurons and Cognition · Quantitative Biology 2025-12-01 Nicolás Hinrichs , Noah Guzmán , Melanie Weber

We present a didactic introduction to spectral Dynamic Causal Modelling (DCM), a Bayesian state-space modelling approach used to infer effective connectivity from non-invasive neuroimaging data. Spectral DCM is currently the most widely…

Neurons and Cognition · Quantitative Biology 2023-09-07 Leonardo Novelli , Karl Friston , Adeel Razi

Quantum-correlated networks distribute quantum resources such as squeezed and entangled states. These states are central to modern quantum technology, including photonic quantum computing, quantum communications, non-destructive biological…

Quantum Physics · Physics 2026-03-24 Stephan Grebien , Julian Gurs , Roman Schnabel , Mikhail Korobko

Symmetries found through automorphisms or graph fibrations provide important insights in network analysis. Symmetries identify clusters of robust synchronization in the network which improves the understanding of the functionality of…

Quantitative Methods · Quantitative Biology 2022-07-27 Ian Leifer , David Phillips , Francesco Sorrentino , Hernán A. Makse

In a sensor network, in practice, the communication among sensors is subject to:(1) errors or failures at random times; (3) costs; and(2) constraints since sensors and networks operate under scarce resources, such as power, data rate, or…

Information Theory · Computer Science 2009-11-13 Soummya Kar , Jose M. F. Moura

Modeling signals as linear combinations of atoms from a dictionary is ubiquitous in modern signal processing. In the finite-dimensional setting, whenever atoms depend nonlinearly upon unknown parameters, the signal model is said to be…

Signal Processing · Electrical Eng. & Systems 2026-05-04 Santos Michelena , Maxime Ferreira Da Costa , José Picheral

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

Machine Learning · Statistics 2026-01-06 Haoran Zhan , Yingcun Xia