English
Related papers

Related papers: StableGrad: Backward Scale Control without Batch N…

200 papers

There is a significant performance gap between Binary Neural Networks (BNNs) and floating point Deep Neural Networks (DNNs). We propose to improve the binary training method, by introducing a new regularization function that encourages…

Machine Learning · Computer Science 2020-04-22 Sajad Darabi , Mouloud Belbahri , Matthieu Courbariaux , Vahid Partovi Nia

Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy. However, we demonstrate that BN comes with a fundamental drawback: it incentivizes the model…

Machine Learning · Computer Science 2022-07-05 Saeid Asgari Taghanaki , Ali Gholami , Fereshte Khani , Kristy Choi , Linh Tran , Ran Zhang , Aliasghar Khani

In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of weights of the DNNs, such as the Frobenius and spectral…

Machine Learning · Computer Science 2019-05-23 Mete Ozay

Depth completion, inferring dense depth maps from sparse measurements, is crucial for robust 3D perception. Although deep learning based methods have made tremendous progress in this problem, these models cannot generalize well across…

Computer Vision and Pattern Recognition · Computer Science 2024-10-25 Haotian Wang , Meng Yang , Xinhu Zheng , Gang Hua

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture…

Computation and Language · Computer Science 2026-02-02 Chao Wang , Bei Li , Jiaqi Zhang , Xinyu Liu , Yuchun Fan , Linkun Lyu , Xin Chen , Jingang Wang , Tong Xiao , Peng Pei , Xunliang Cai

We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network. We derive constraints on the parameterization under which the controller…

Systems and Control · Electrical Eng. & Systems 2024-04-15 Neelay Junnarkar , He Yin , Fangda Gu , Murat Arcak , Peter Seiler

Despite their impressive performance, contemporary neural networks often lack structural safeguards that promote stable learning and interpretable behavior. In this work, we introduce a reformulation of layer-level transformations that…

Machine Learning · Computer Science 2025-08-04 Saleh Nikooroo , Thomas Engel

Power distribution networks are approaching their voltage stability boundaries due to the severe voltage violations and the inadequate reactive power reserves caused by the increasing renewable generations and dynamic loads. In the broad…

Optimization and Control · Mathematics 2022-08-18 Wanjun Huang , Changhong Zhao

The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods…

Machine Learning · Statistics 2019-06-12 Julien Launay , Iacopo Poli , Florent Krzakala

In this work, we study physics-informed neural networks (PINNs) constrained by partial differential equations (PDEs) and their application in approximating PDEs with two characteristic scales. From a continuous perspective, our formulation…

Optimization and Control · Mathematics 2024-09-06 Michael Hintermüller , Denis Korolev

We consider the problem of denoising with the help of prior information taken from a database of clean signals or images. Denoising with variational methods is very efficient if a regularizer well adapted to the nature of the data is…

Machine Learning · Computer Science 2023-10-06 Hui Shi , Yann Traonmilin , J-F Aujol

In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network training, based on adaptive estimates of feasible region via branch-and-bound. The method is based on the assumption of Lipschitz continuity in…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Yuanwei Wu , Ziming Zhang , Guanghui Wang

Recurrent neural networks (RNNs) hold immense potential for computations due to their Turing completeness and sequential processing capabilities, yet existing methods for their training encounter efficiency challenges. Backpropagation…

Machine Learning · Computer Science 2024-10-02 Jesus Garcia Fernandez , Sander Keemink , Marcel van Gerven

With growing investigations into solving partial differential equations by physics-informed neural networks (PINNs), more accurate and efficient PINNs are required to meet the practical demands of scientific computing. One bottleneck of…

Machine Learning · Computer Science 2025-10-29 Tianchi Yu , Yiming Qi , Ivan Oseledets , Shiyi Chen

Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure…

Machine Learning · Computer Science 2026-02-19 Yixiao Qian , Jiaxu Liu , Zewei Xia , Song Chen , Chao Xu , Shengze Cai

Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…

Machine Learning · Computer Science 2020-06-25 Jary Pomponi , Simone Scardapane , Vincenzo Lomonaco , Aurelio Uncini

Partial differential equations (PDEs) are an essential computational kernel in physics and engineering. With the advance of deep learning, physics-informed neural networks (PINNs), as a mesh-free method, have shown great potential for fast…

Machine Learning · Computer Science 2023-06-19 Junjun Yan , Xinhai Chen , Zhichao Wang , Enqiang Zhoui , Jie Liu

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

In deep learning, Residual Networks (ResNets) have proven effective in addressing the vanishing gradient problem, allowing for the successful training of very deep networks. However, skip connections in ResNets can lead to gradient overlap,…

Machine Learning · Computer Science 2024-11-18 Juyoung Yun

Robust fine-tuning aims to adapt large foundation models to downstream tasks while preserving their robustness to distribution shifts. Existing methods primarily focus on constraining and projecting current model towards the pre-trained…

Machine Learning · Computer Science 2025-06-24 Chengyue Huang , Junjiao Tian , Brisa Maneechotesuwan , Shivang Chopra , Zsolt Kira
‹ Prev 1 8 9 10 Next ›