English
Related papers

Related papers: Complex fractal trainability boundary can arise fr…

200 papers

In the realm of fractal geometry, intricate structures emerge from simple iterative processes that partition parameter spaces into regions of stability and instability. Likewise, training large language models involves iteratively applying…

Machine Learning · Computer Science 2025-02-18 Bahman Torkamandi

Some fractals -- for instance those associated with the Mandelbrot and quadratic Julia sets -- are computed by iterating a function, and identifying the boundary between hyperparameters for which the resulting series diverges or remains…

Machine Learning · Computer Science 2024-02-12 Jascha Sohl-Dickstein

Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates…

Machine Learning · Computer Science 2020-10-16 Guillermo Ortiz-Jimenez , Apostolos Modas , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard

The fractal dimension provides a statistical index of object complexity by studying how the pattern changes with the measuring scale. Although useful in several classification tasks, the fractal dimension is under-explored in deep learning…

Machine Learning · Computer Science 2024-01-10 Julia El Zini , Bassel Musharrafieh , Mariette Awad

Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. There is a recent and growing body of literature that proposes the framework of fractals to…

Machine Learning · Computer Science 2024-11-04 Charlie B. Tan , Inés García-Redondo , Qiquan Wang , Michael M. Bronstein , Anthea Monod

Deep Neural Networks (DNNs) rely on inherent fluctuations in their internal parameters (weights and biases) to effectively navigate the complex optimization landscape and achieve robust performance. While these fluctuations are recognized…

Machine Learning · Computer Science 2025-11-14 Darsh Pareek , Umesh Kumar , Ruthu Rao , Ravi Janjam

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

The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, existing methods to solve these issues, such as adversarial…

Machine Learning · Computer Science 2023-01-11 Suraj Srinivas , Kyle Matoba , Himabindu Lakkaraju , Francois Fleuret

We study the geometric properties of random neural networks by investigating the boundary volumes of their excursion sets for different activation functions, as the depth increases. More specifically, we show that, for activations which are…

Probability · Mathematics 2026-01-29 Simmaco Di Lillo , Domenico Marinucci , Michele Salvi , Stefano Vigogna

Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in…

Machine Learning · Computer Science 2026-02-26 Jianneng Yu , Alexandre V. Morozov

Existing analyses of neural network training often operate under the unrealistic assumption of an extremely small learning rate. This lies in stark contrast to practical wisdom and empirical studies, such as the work of J. Cohen et al.…

Machine Learning · Computer Science 2023-10-20 Kwangjun Ahn , Sébastien Bubeck , Sinho Chewi , Yin Tat Lee , Felipe Suarez , Yi Zhang

Generalization error bounds for deep neural networks trained by stochastic gradient descent (SGD) are derived by combining a dynamical control of an appropriate parameter norm and the Rademacher complexity estimate based on parameter norms.…

Machine Learning · Computer Science 2023-05-30 Mingze Wang , Chao Ma

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

Machine Learning · Computer Science 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

The local geometry of high dimensional neural network loss landscapes can both challenge our cherished theoretical intuitions as well as dramatically impact the practical success of neural network training. Indeed recent works have observed…

Machine Learning · Computer Science 2019-10-15 Stanislav Fort , Surya Ganguli

We propose a machine learning approach to address a key challenge in materials science: predicting how fractures propagate in brittle materials under stress, and how these materials ultimately fail. Our methods use deep learning and train…

Fractals are geometric shapes that can display complex and self-similar patterns found in nature (e.g., clouds and plants). Recent works in visual recognition have leveraged this property to create random fractal images for model…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Cheng-Hao Tu , Hong-You Chen , David Carlyn , Wei-Lun Chao

It has been observed that the input space of deep neural network classifiers can exhibit `fragmentation', where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the…

While deep learning has resulted in major breakthroughs in many application domains, the frameworks commonly used in deep learning remain fragile to artificially-crafted and imperceptible changes in the data. In response to this fragility,…

Machine Learning · Computer Science 2020-11-03 Alexander Robey , Hamed Hassani , George J. Pappas

Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…

Computer Vision and Pattern Recognition · Computer Science 2020-03-12 Byungju Kim , Junmo Kim

We introduce a design strategy for neural network macro-architecture based on self-similarity. Repeated application of a simple expansion rule generates deep networks whose structural layouts are precisely truncated fractals. These networks…

Computer Vision and Pattern Recognition · Computer Science 2017-05-30 Gustav Larsson , Michael Maire , Gregory Shakhnarovich
‹ Prev 1 2 3 10 Next ›