English
Related papers

Related papers: Explaining Landscape Connectivity of Low-cost Solu…

200 papers

Hyperparameters greatly impact models' capabilities; however, modern models are too large for extensive search. Instead, researchers design recipes that train well across scales based on their understanding of the hyperparameters. Despite…

Machine Learning · Computer Science 2025-10-06 Nicholas Lourie , He He , Kyunghyun Cho

Studying neural network loss landscapes provides insights into the nature of the underlying optimization problems. Unfortunately, loss landscapes are notoriously difficult to visualize in a human-comprehensible fashion. One common way to…

Machine Learning · Computer Science 2022-02-04 Tiffany Vlaar , Jonathan Frankle

Optimizing paths on networks is crucial for many applications, from subway traffic to Internet communication. As global path optimization that takes account of all path-choices simultaneously is computationally hard, most existing routing…

Physics and Society · Physics 2013-09-05 Chi Ho Yeung , David Saad , K. Y. Michael Wong

Recent progress towards unraveling the hidden geometric organization of real multiplexes revealed significant correlations across the hyperbolic node coordinates in different network layers, which facilitated applications like trans-layer…

Social and Information Networks · Computer Science 2019-01-29 Fragkiskos Papadopoulos , Kaj-Kolja Kleineberg

This paper shows that every sublevel set of the loss function of a class of deep over-parameterized neural nets with piecewise linear activation functions is connected and unbounded. This implies that the loss has no bad local valleys and…

Machine Learning · Computer Science 2019-05-15 Quynh Nguyen

Multilayer networks describe well many real interconnected communication and transportation systems, ranging from computer networks to multimodal mobility infrastructures. Here, we introduce a model in which the nodes have a limited…

Physics and Society · Physics 2018-02-22 Sabato Manfredi , Edmondo Di Tucci , Vito Latora

We propose a network characterization of combinatorial fitness landscapes by adapting the notion of inherent networks proposed for energy surfaces. We use the well-known family of NK landscapes as an example. In our case the inherent…

Neural and Evolutionary Computing · Computer Science 2008-10-21 Sébastien Verel , Gabriela Ochoa , Marco Tomassini

We construct and investigate Boolean networks that follow a given reliable trajectory in state space, which is insensitive to fluctuations in the updating schedule, and which is also robust against noise. Robustness is quantified as the…

Biological Physics · Physics 2010-12-02 Christoph Schmal , Tiago P. Peixoto , Barbara Drossel

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

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

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,…

Disordered Systems and Neural Networks · Physics 2013-12-13 Orestis Georgiou , Carl P. Dettmann , Justin Coon

A trajectorial large deviation principle is established in a mean field thermodynamic limit for a multiclass loss network with diminishing rates, which may have several stable equilibria. The large deviation limit is identified as a unique…

Probability · Mathematics 2022-05-23 Anatolii A. Puhalskii

One of the main challenges in modern deep learning is to understand why such over-parameterized models perform so well when trained on finite data. A way to analyze this generalization concept is through the properties of the associated…

Machine Learning · Computer Science 2023-07-11 Alison Pouplin , Hrittik Roy , Sidak Pal Singh , Georgios Arvanitidis

The generalization mystery of overparametrized deep nets has motivated efforts to understand how gradient descent (GD) converges to low-loss solutions that generalize well. Real-life neural networks are initialized from small random values…

Machine Learning · Computer Science 2021-11-10 Kaifeng Lyu , Zhiyuan Li , Runzhe Wang , Sanjeev Arora

Although deep networks have recently emerged as the model of choice for many computer vision problems, in order to yield good results they often require time-consuming architecture search. To combat the complexity of design choices, prior…

Computer Vision and Pattern Recognition · Computer Science 2018-12-18 Karim Ahmed , Lorenzo Torresani

Large optimal transport problems can be approached via domain decomposition, i.e. by iteratively solving small partial problems independently and in parallel. Convergence to the global minimizers under suitable assumptions has been shown in…

Optimization and Control · Mathematics 2021-06-16 Mauro Bonafini , Ismael Medina , Bernhard Schmitzer

The interactions between the components of many real-world systems are best modelled by networks with multiple layers. Different theories have been proposed to explain how multilayered connections affect the linear stability of…

Physics and Society · Physics 2022-03-25 Charo I. del Genio , Sergio Faci-Lázaro , Jesús Gómez-Gardeñes , Stefano Boccaletti

The local optima network model has proved useful in the past in connection with combinatorial optimization problems. Here we examine its extension to the real continuous function domain. Through a sampling process, the model builds a…

Statistical Mechanics · Physics 2022-12-21 Marco Tomassini

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

We explore element-wise convex combinations of two permutation-aligned neural network parameter vectors $\Theta_A$ and $\Theta_B$ of size $d$. We conduct extensive experiments by examining various distributions of such model combinations…

Machine Learning · Computer Science 2023-08-23 Adrián Csiszárik , Melinda F. Kiss , Péter Kőrösi-Szabó , Márton Muntag , Gergely Papp , Dániel Varga
‹ Prev 1 3 4 5 6 7 10 Next ›