English
Related papers

Related papers: Geometric and Dynamic Scaling in Deep Transformers

200 papers

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current…

Machine Learning · Computer Science 2023-03-02 Haiteng Zhao , Shuming Ma , Dongdong Zhang , Zhi-Hong Deng , Furu Wei

The scattering transform is a multilayered wavelet-based deep learning architecture that acts as a model of convolutional neural networks. Recently, several works have introduced generalizations of the scattering transform for non-Euclidean…

Machine Learning · Statistics 2023-06-30 Michael Perlmutter , Alexander Tong , Feng Gao , Guy Wolf , Matthew Hirn

Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlational with respect to token prediction formation. Meanwhile, causal interventions expose…

Machine Learning · Computer Science 2026-05-27 Shahar Haim , Daniel C McNamee

A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inputs or components. There is however still a dearth of work…

Computation and Language · Computer Science 2023-10-12 Timothee Mickus , Raúl Vázquez

This work investigates the generalization behavior of deep neural networks (DNNs), focusing on the phenomenon of "fooling examples," where DNNs confidently classify inputs that appear random or unstructured to humans. To explore this…

Machine Learning · Computer Science 2025-08-22 Yen-Lung Lai , Zhe Jin

Topological Data Analysis (TDA) provides tools to describe the shape of data, but integrating topological features into deep learning pipelines remains challenging, especially when preserving local geometric structure rather than…

Machine Learning · Computer Science 2026-04-21 Elena Xinyi Wang , Arnur Nigmetov , Dmitriy Morozov

Geometric data pruning methods, while practical for leveraging pretrained models, are fundamentally unstable. Their reliance on extrinsic geometry renders them highly sensitive to latent space perturbations, causing performance to degrade…

Machine Learning · Computer Science 2026-05-11 Arjun Roy , Prajna G. Malettira , Manish Nagaraj , Kaushik Roy

Graph Convolutional Networks (GCNs) are known to suffer from performance degradation as the number of layers increases, which is usually attributed to over-smoothing. Despite the apparent consensus, we observe that there exists a…

Machine Learning · Computer Science 2021-10-29 Weilin Cong , Morteza Ramezani , Mehrdad Mahdavi

Active area of research in AI is the theory of manifold learning and finding lower-dimensional manifold representation on how we can learn geometry from data for providing better quality curated datasets. There are however various issues…

Machine Learning · Computer Science 2024-10-16 Liubov Tupikina , Kathuria Hritika

The reconstruction of a high resolution image given a low resolution observation is an ill-posed inverse problem in imaging. Deep learning methods rely on training data to learn an end-to-end mapping from a low-resolution input to a…

Image and Video Processing · Electrical Eng. & Systems 2023-07-19 Iman Marivani , Evaggelia Tsiligianni , Bruno Cornelis , Nikos Deligiannis

Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not…

Computer Vision and Pattern Recognition · Computer Science 2019-01-07 Fisher Yu , Dequan Wang , Evan Shelhamer , Trevor Darrell

Manifold learning builds on the "manifold hypothesis," which posits that data in high-dimensional datasets are drawn from lower-dimensional manifolds. Current tools generate global embeddings of data, rather than the local maps used to…

Machine Learning · Computer Science 2025-08-28 Serena Hughes , Timothy Hamilton , Tom Kolokotrones , Eric J. Deeds

We consider dynamical and geometrical aspects of deep learning. For many standard choices of layer maps we display semi-invariant metrics which quantify differences between data or decision functions. This allows us, when considering random…

Machine Learning · Computer Science 2021-04-23 Benny Avelin , Anders Karlsson

Geophysical inversion attempts to estimate the distribution of physical properties in the Earth's interior from observations collected at or above the surface. Inverse problems are commonly posed as least-squares optimization problems in…

Geophysics · Physics 2019-05-22 Vladimir Puzyrev

Our understanding of learning dynamics of deep neural networks (DNNs) remains incomplete. Recent research has begun to uncover the mathematical principles underlying these networks, including the phenomenon of "Neural Collapse", where…

Machine Learning · Computer Science 2024-02-13 Bradley T. Baker , Barak A. Pearlmutter , Robyn Miller , Vince D. Calhoun , Sergey M. Plis

Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…

Machine Learning · Computer Science 2023-04-10 Roman Worschech , Bernd Rosenow

Oversmoothing has long been identified as a major limitation of Graph Neural Networks (GNNs): input node features are smoothed at each layer and converge to a non-informative representation, if the weights of the GNN are sufficiently…

Machine Learning · Computer Science 2026-03-16 Nicolas Keriven

Manifold learning methods are an invaluable tool in today's world of increasingly huge datasets. Manifold learning algorithms can discover a much lower-dimensional representation (embedding) of a high-dimensional dataset through non-linear…

Machine Learning · Computer Science 2021-08-24 Andrew Lensen , Bing Xue , Mengjie Zhang

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A widely used strategy, the gradient difference method, applies…

Machine Learning · Computer Science 2026-03-19 Arpit Garg , Hemanth Saratchandran , Ravi Garg , Simon Lucey