English
Related papers

Related papers: Barcodes as Summary of Loss Function Topology

200 papers

In this work, we study the perception problem for sampled surfaces (possibly with boundary) using tools from computational topology, specifically, how to identify their underlying topology starting from point-cloud samples in space, such as…

Computational Geometry · Computer Science 2024-10-17 Franco Coltraro , Jaume Amorós , Maria Alberich-Carramiñana , Carme Torras

Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an…

Machine Learning · Statistics 2019-05-09 Arild Nøkland , Lars Hiller Eidnes

There has been a lot of recent interest in trying to characterize the error surface of deep models. This stems from a long standing question. Given that deep networks are highly nonlinear systems optimized by local gradient methods, why do…

Machine Learning · Statistics 2017-02-20 Grzegorz Swirszcz , Wojciech Marian Czarnecki , Razvan Pascanu

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

In practice, since many communication networks are huge in scale, or complicated in structure, or even dynamic, the predesigned linear network codes based on the network topology is impossible even if the topological structure is known.…

Information Theory · Computer Science 2013-02-26 Xuan Guang , Fang-Wei Fu

Multi-robot motion planning problems often have many local minima. It is essential to visualize those local minima such that we can better understand, debug and interact with multi-robot systems. Towards this goal, we present the…

Robotics · Computer Science 2020-04-30 Andreas Orthey , Marc Toussaint

Viewing neural network models in terms of their loss landscapes has a long history in the statistical mechanics approach to learning, and in recent years it has received attention within machine learning proper. Among other things, local…

Machine Learning · Computer Science 2021-12-14 Yaoqing Yang , Liam Hodgkinson , Ryan Theisen , Joe Zou , Joseph E. Gonzalez , Kannan Ramchandran , Michael W. Mahoney

Blood vessel segmentation is one of the most studied topics in computer vision, due to its relevance in daily clinical practice. Despite the evolution the field has been facing, especially after the dawn of deep learning, important…

Image and Video Processing · Electrical Eng. & Systems 2021-08-02 R. J. Araújo , J. S. Cardoso , H. P. Oliveira

Under mild assumptions, we investigate the geometry of the loss landscape for two-layer neural networks in the vicinity of global minima. Utilizing novel techniques, we demonstrate: (i) how global minima with zero generalization error…

Machine Learning · Computer Science 2025-04-11 Leyang Zhang , Yaoyu Zhang , Tao Luo

Understanding the common topological characteristics of the human brain network across a population is central to understanding brain functions. The abstraction of human connectome as a graph has been pivotal in gaining insights on the…

Quantitative Methods · Quantitative Biology 2023-04-26 Soumya Das , D. Vijay Anand , Moo K. Chung

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

Quantification of the stationary points and the associated basins of attraction of neural network loss surfaces is an important step towards a better understanding of neural network loss surfaces at large. This work proposes a novel method…

Machine Learning · Computer Science 2019-01-10 Anna Sergeevna Bosman , Andries Engelbrecht , Mardé Helbig

High-throughput methods for yielding the set of connections in a neural system, the connectome, are now being developed. This tutorial describes ways to analyze the topological and spatial organization of the connectome at the macroscopic…

Neurons and Cognition · Quantitative Biology 2011-12-23 Marcus Kaiser

Training neural networks means solving a high-dimensional optimization problem. Normally the goal is to minimize a loss function that depends on what is called the network function, or in other words the function that gives the network…

Machine Learning · Computer Science 2022-11-15 Umberto Michelucci

We construct random Morse functions on surfaces by random walk and compute related distributions. We study the space of Morse functions through these random variables. We consider subspaces characterized by the surfaces with boundary…

Probability · Mathematics 2025-08-28 Boldizsar Kalmar

By using the viewpoint of modern computational algebraic geometry, we explore properties of the optimization landscapes of the deep linear neural network models. After clarifying on the various definitions of "flat" minima, we show that the…

Machine Learning · Statistics 2018-10-19 Dhagash Mehta , Tianran Chen , Tingting Tang , Jonathan D. Hauenstein

Due to the success of deep learning to solving a variety of challenging machine learning tasks, there is a rising interest in understanding loss functions for training neural networks from a theoretical aspect. Particularly, the properties…

Machine Learning · Statistics 2017-11-01 Yi Zhou , Yingbin Liang

We consider a crucial aspect of self-organization of a sensor network consisting of a large set of simple sensor nodes with no location hardware and only very limited communication range. After having been distributed randomly in a given…

Data Structures and Algorithms · Computer Science 2007-05-23 Sandor P. Fekete , Alexander Kroeller , Dennis Pfisterer , Stefan Fischer , Carsten Buschmann

Partitioned neural network functions are used to approximate the solution of partial differential equations. The problem domain is partitioned into non-overlapping subdomains and the partitioned neural network functions are defined on the…

Numerical Analysis · Mathematics 2023-12-25 Deok-Kyu Jang , Kyungsoo Kim , Hyea Hyun Kim

The existence of local minima for one-hidden-layer ReLU networks has been investigated theoretically in [8]. Based on the theory, in this paper, we first analyze how big the probability of existing local minima is for 1D Gaussian data and…

Machine Learning · Computer Science 2020-06-17 Bo Liu