English
Related papers

Related papers: Numerical Fragility in Transformers: A Layer-wise …

200 papers

Deep convolutional neural networks often perform poorly when faced with datasets that suffer from quantity imbalances and classification difficulties. Despite advances in the field, existing two-stage approaches still exhibit dataset bias…

Machine Learning · Computer Science 2023-03-16 Liang Xu , Yi Cheng , Fan Zhang , Bingxuan Wu , Pengfei Shao , Peng Liu , Shuwei Shen , Peng Yao , Ronald X. Xu

In this paper, we propose a simple yet effective method to stabilize extremely deep Transformers. Specifically, we introduce a new normalization function (DeepNorm) to modify the residual connection in Transformer, accompanying with…

Computation and Language · Computer Science 2022-03-02 Hongyu Wang , Shuming Ma , Li Dong , Shaohan Huang , Dongdong Zhang , Furu Wei

Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise…

Machine Learning · Computer Science 2026-05-08 Amir Rezaei Balef , Mykhailo Koshil , Katharina Eggensperger

Training instabilities in deep networks - loss spikes, oscillatory convergence, and gradient pathologies - are empirically prevalent but lack a rigorous operator-theoretic explanation. We show that the linearized update operators for…

Machine Learning · Computer Science 2026-05-25 Souvik Ghosh

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency. The main challenge is how to measure such hardness and decide the required depths (i.e., layers) to conduct.…

Computation and Language · Computer Science 2020-12-17 Yijin Liu , Fandong Meng , Jie Zhou , Yufeng Chen , Jinan Xu

The same machine learning model running on different edge devices may produce highly-divergent outputs on a nearly-identical input. Possible reasons for the divergence include differences in the device sensors, the device's signal…

Machine Learning · Computer Science 2020-10-20 Eyal Cidon , Evgenya Pergament , Zain Asgar , Asaf Cidon , Sachin Katti

Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…

Machine Learning · Computer Science 2025-02-14 Bhavya Vasudeva , Deqing Fu , Tianyi Zhou , Elliott Kau , Youqi Huang , Vatsal Sharan

Synchronous federated learning (FL) scales poorly with the number of clients due to the straggler effect. Algorithms like FedAsync and GeneralizedFedAsync address this limitation by enabling asynchronous communication between clients and…

Machine Learning · Computer Science 2025-10-23 Abdelkrim Alahyane , Céline Comte , Matthieu Jonckheere , Éric Moulines

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness on graph-based tasks. However, their predictive confidence is often miscalibrated, typically exhibiting under-confidence, which harms the reliability of their…

Machine Learning · Computer Science 2025-09-30 Jincheng Huang , Jie Xu , Xiaoshuang Shi , Ping Hu , Lei Feng , Xiaofeng Zhu

Due to their architecture and how they are trained, artificial neural networks are typically not robust toward pruning or shuffling layers at test time. However, such properties would be desirable for different applications, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Matthias Freiberger , Peter Kun , Anders Sundnes Løvlie , Sebastian Risi

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…

Machine Learning · Computer Science 2024-01-10 Shehzaad Dhuliawala , Mrinmaya Sachan , Carl Allen

We propose a homogeneous multilayer perceptron parameterization with polynomial hidden layer width pattern and analyze its training dynamics under stochastic gradient descent with depthwise gradient scaling in a general supervised learning…

Machine Learning · Computer Science 2025-05-20 Dávid Terjék

Neural scaling laws describe how language model loss decreases with parameters and data, but treat architecture as interchangeable--a billion parameters could arise from a shallow-wide model (10 layers & 8,192 hidden dimension) or a…

Machine Learning · Computer Science 2026-01-30 Md Muhtasim Munif Fahim , Md Rezaul Karim

As an emerging type of Neural Networks (NNs), Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving. In this paper, we study the robustness problem of Transformers, a key characteristic as low…

Machine Learning · Computer Science 2024-12-03 Brian Hsuan-Cheng Liao , Chih-Hong Cheng , Hasan Esen , Alois Knoll

Layer formation in a thermally destabilized fluid with stable density gradient has been observed in laboratory experiments and has been proposed as a mechanism for mixing molecular weight in late stages of stellar evolution in regions which…

Astrophysics · Physics 2007-05-23 Joseph A. Biello

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

Deep Neural Networks have shown promising classification performance when predicting certain biomarkers from Whole Slide Images in digital pathology. However, the calibration of the networks' output probabilities is often not evaluated.…

Image and Video Processing · Electrical Eng. & Systems 2023-12-18 Alexander Kurz , Hendrik A. Mehrtens , Tabea-Clara Bucher , Titus J. Brinker

Training neural network classifiers on datasets with label noise poses a risk of overfitting them to the noisy labels. To address this issue, researchers have explored alternative loss functions that aim to be more robust. The…

Machine Learning · Computer Science 2024-08-23 William Toner , Amos Storkey

Various layer-skipping methods have been proposed to accelerate token generation in large language models (LLMs). However, limited attention has been paid to a fundamental question: How do computational demands vary across the generation of…

Computation and Language · Computer Science 2025-10-10 Xuan Luo , Weizhi Wang , Xifeng Yan

LLMs for clinical decision support often fail under small but clinically meaningful input shifts such as masking a symptom or negating a finding, despite high performance on static benchmarks. These reasoning failures frequently go…

Machine Learning · Computer Science 2025-07-30 Raj Krishnan Vijayaraj
‹ Prev 1 3 4 5 6 7 10 Next ›