English
Related papers

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

200 papers

We provide an up-to-date view of the structure of the energy landscape of the low autocorrelation binary sequences problem, a typical representative of the $NP$-hard class. To study the landscape features of interest we use the local optima…

Statistical Mechanics · Physics 2022-04-11 Marco Tomassini

Traditional landscape analysis of deep neural networks aims to show that no sub-optimal local minima exist in some appropriate sense. From this, one may be tempted to conclude that descent algorithms which escape saddle points will reach a…

Machine Learning · Computer Science 2020-01-01 Shiyu Liang , Ruoyu Sun , R. Srikant

Dissipation in amorphous solids at low frequencies is commonly attributed to activated transitions of isolated two-level systems (TLS) that come in resonance with elastic or electric fields. Materials with low mechanical or dielectric loss…

Materials Science · Physics 2026-04-14 Steven Blaber , Daniel Bruns , Jörg Rottler

Sampling-based path planning algorithms usually implement uniform sampling methods to search the state space. However, uniform sampling may lead to unnecessary exploration in many scenarios, such as the environment with a few dead ends. Our…

Robotics · Computer Science 2022-07-25 Han Ma , Chenming Li , Jianbang Liu , Jiankun Wang , Max Q. -H. Meng

Optimization methods play a crucial role in modern machine learning, powering the remarkable empirical achievements of deep learning models. These successes are even more remarkable given the complex non-convex nature of the loss landscape…

Machine Learning · Computer Science 2024-10-28 Rustem Islamov , Niccolò Ajroldi , Antonio Orvieto , Aurelien Lucchi

In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly…

Neural and Evolutionary Computing · Computer Science 2017-03-23 Shumeet Baluja

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

Nodes in ad hoc networks with randomly oriented directional antenna patterns typically have fewer short links and more long links which can bridge together otherwise isolated subnetworks. This network feature is known to improve overall…

Information Theory · Computer Science 2017-06-29 Orestis Georgiou , Carl P. Dettmann , Justin P. Coon

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Training a neural network requires navigating a high-dimensional, non-convex loss surface to find parameters that minimize this loss. In many ways, it is surprising that optimizers such as stochastic gradient descent and ADAM can reliably…

Machine Learning · Computer Science 2026-02-06 Conor Rowan , Finn Murphy-Blanchard

Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topological connectivity of neural networks is also important.…

Computer Vision and Pattern Recognition · Computer Science 2020-08-20 Kun Yuan , Quanquan Li , Jing Shao , Junjie Yan

Routing information through networks is a universal phenomenon in both natural and manmade complex systems. When each node has full knowledge of the global network connectivity, finding short communication paths is merely a matter of…

Physics and Society · Physics 2009-05-20 Marian Boguna , Dmitri Krioukov , kc claffy

One of the major concerns for neural network training is that the non-convexity of the associated loss functions may cause bad landscape. The recent success of neural networks suggests that their loss landscape is not too bad, but what…

Machine Learning · Computer Science 2023-07-19 Ruoyu Sun , Dawei Li , Shiyu Liang , Tian Ding , R Srikant

While the optimization problem behind deep neural networks is highly non-convex, it is frequently observed in practice that training deep networks seems possible without getting stuck in suboptimal points. It has been argued that this is…

Machine Learning · Computer Science 2017-06-14 Quynh Nguyen , Matthias Hein

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

Connectivity is a fundamental structural feature of a network that determines the outcome of any dynamics that happens on top of it. However, an analytical approach to obtain connection probabilities between nodes associated to paths of…

Atmospheric and Oceanic Physics · Physics 2021-04-28 Enrico Ser-Giacomi , Terence Legrand , Ismael Hernandez-Carrasco , Vincent Rossi

It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space over which test set accuracy is maintained. Under some…

Machine Learning · Computer Science 2023-01-24 Jeevesh Juneja , Rachit Bansal , Kyunghyun Cho , João Sedoc , Naomi Saphra

It is shown that for deep neural networks, a single wide layer of width $N+1$ ($N$ being the number of training samples) suffices to prove the connectivity of sublevel sets of the training loss function. In the two-layer setting, the same…

Machine Learning · Computer Science 2021-01-22 Quynh Nguyen

Recently, the property of connectedness has been claimed to give a strong motivation on the design of local search techniques for multiobjective combinatorial optimization (MOCO). Indeed, when connectedness holds, a basic Pareto local…

Neural and Evolutionary Computing · Computer Science 2012-07-20 Sébastien Verel , Arnaud Liefooghe , Jérémie Humeau , Laetitia Jourdan , Clarisse Dhaenens

We introduce a general theoretical framework, designed for the study of gradient optimisation of deep neural networks, that encompasses ubiquitous architecture choices including batch normalisation, weight normalisation and skip…

Machine Learning · Computer Science 2023-12-05 Lachlan Ewen MacDonald , Jack Valmadre , Hemanth Saratchandran , Simon Lucey