English
Related papers

Related papers: Neural collapse in the orthoplex regime

200 papers

Neural network models and deep models are one of the leading and state of the art models in machine learning. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such…

Machine Learning · Computer Science 2018-07-17 Soufiane Belharbi

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Machine Learning · Computer Science 2024-03-01 Zhen Qin , Xuwei Tan , Zhihui Zhu

With the ever-increasing complexity of large-scale pre-trained models coupled with a shortage of labeled data for downstream training, transfer learning has become the primary approach in many fields, including natural language processing,…

Machine Learning · Computer Science 2024-07-22 Xiao Li , Sheng Liu , Jinxin Zhou , Xinyu Lu , Carlos Fernandez-Granda , Zhihui Zhu , Qing Qu

Low dimensional structures appear ubiquitously in the eigenspectra of deep learning matrices in classification networks trained in the overparameterized regime. While theoretical advances have aimed to explain this phenomenology, they…

Machine Learning · Computer Science 2026-05-28 Connall Garrod , Jonathan P. Keating

Artificial neural networks have been widely adopted as ansatzes to study classical and quantum systems. However, some notably hard systems such as those exhibiting glassiness and frustration have mainly achieved unsatisfactory results…

Disordered Systems and Neural Networks · Physics 2022-04-26 Estelle M. Inack , Stewart Morawetz , Roger G. Melko

Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Paul Gavrikov , Janis Keuper , Margret Keuper

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially…

Machine Learning · Computer Science 2018-06-05 Simon S. Du , Surbhi Goel

Neural networks offer good approximation to many tasks but consistently fail to reach perfect generalization, even when theoretical work shows that such perfect solutions can be expressed by certain architectures. Using the task of formal…

Computation and Language · Computer Science 2024-06-07 Nur Lan , Emmanuel Chemla , Roni Katzir

Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial ones, which are common in real-world settings. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Michael A. Alcorn , Qi Li , Zhitao Gong , Chengfei Wang , Long Mai , Wei-Shinn Ku , Anh Nguyen

One of the most prominent attributes of Neural Networks (NNs) constitutes their capability of learning to extract robust and descriptive features from high dimensional data, like images. Hence, such an ability renders their exploitation as…

Computer Vision and Pattern Recognition · Computer Science 2021-07-14 Ioannis Kansizoglou , Loukas Bampis , Antonios Gasteratos

Model reduction is essential for real-time simulation of deformable objects. Linear techniques such as PCA provide structured and predictable behavior, but their limited expressiveness restricts accuracy under large or nonlinear…

Graphics · Computer Science 2026-01-28 Shixun Huang , Eitan Grinspun , Yue Chang

Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima.…

Machine Learning · Computer Science 2016-02-25 Zachary C. Lipton

Using vanilla NeuralODEs to model large and/or complex systems often fails due two reasons: Stability and convergence. NeuralODEs are capable of describing stable as well as instable dynamic systems. Selecting an appropriate numerical…

Machine Learning · Computer Science 2023-02-23 Tobias Thummerer , Lars Mikelsons

We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex) functions. Our networks implicitly represent both the support and gauge functions of a convex body. We prove a universal…

Optimization and Control · Mathematics 2026-05-06 Eloi Martinet

In this paper, we present a Mirroring Neural Network architecture to perform non-linear dimensionality reduction and Object Recognition using a reduced lowdimensional characteristic vector. In addition to dimensionality reduction, the…

Computer Vision and Pattern Recognition · Computer Science 2008-12-13 Dasika Ratna Deepthi , Sujeet Kuchibhotla , K. Eswaran

Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us to rethink generalization by bringing forth new phenomena,…

Machine Learning · Statistics 2020-12-01 Vatsal Shah , Soumya Basu , Anastasios Kyrillidis , Sujay Sanghavi

Alignment, the tendency of adjacent weight matrices in deep networks to develop compatible subspace orientations, underlies gradient flow, Neural Collapse, and representation similarity across architectures. Despite extensive empirical…

Machine Learning · Computer Science 2026-05-12 Jingchuan Xiao , Xinyi Sui , Cihan Ruan

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely…

Machine Learning · Computer Science 2026-01-16 Haoran Su , Chenyu You

While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study the case of binary classification and prove various…

Machine Learning · Computer Science 2020-12-15 Remi Tachet , Mohammad Pezeshki , Samira Shabanian , Aaron Courville , Yoshua Bengio
‹ Prev 1 8 9 10 Next ›