English
Related papers

Related papers: u-$\mu$P: The Unit-Scaled Maximal Update Parametri…

200 papers

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In this work, we show…

Machine Learning · Computer Science 2015-11-04 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

Neural networks have achieved dramatic improvements in recent years and depict the state-of-the-art methods for many real-world tasks nowadays. One drawback is, however, that many of these models are overparameterized, which makes them both…

Machine Learning · Computer Science 2019-12-11 Vinnie Ko , Stefan Oehmcke , Fabian Gieseke

Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…

Machine Learning · Computer Science 2023-12-13 Arnav Chavan , Nahush Lele , Deepak Gupta

Sampling-based motion planning algorithms have been continuously developed for more than two decades. Apart from mobile robots, they are also widely used in manipulator motion planning. Hence, these methods play a key role in collaborative…

Robotics · Computer Science 2023-07-13 Carl Gaebert , Sascha Kaden , Benjamin Fischer , Ulrike Thomas

The task of hyper-parameter optimization (HPO) is burdened with heavy computational costs due to the intractability of optimizing both a model's weights and its hyper-parameters simultaneously. In this work, we introduce a new class of HPO…

Machine Learning · Computer Science 2021-12-14 Mathieu Tuli , Mahdi S. Hosseini , Konstantinos N. Plataniotis

Preserving the performance of a trained model while removing unique characteristics of marked training data points is challenging. Recent research usually suggests retraining a model from scratch with remaining training data or refining the…

Machine Learning · Statistics 2022-03-03 Ga Wu , Masoud Hashemi , Christopher Srinivasa

Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting…

Machine Learning · Computer Science 2019-03-08 Matthew MacKay , Paul Vicol , Jon Lorraine , David Duvenaud , Roger Grosse

Recent advancements in image customization exhibit a wide range of application prospects due to stronger customization capabilities. However, since we humans are more sensitive to faces, a significant challenge remains in preserving…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Yufeng Cheng , Wenxu Wu , Shaojin Wu , Mengqi Huang , Fei Ding , Qian He

As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has never been more pressing. Multi-step planning based…

Machine Learning · Computer Science 2022-11-18 Lucio M. Dery , Abram L. Friesen , Nando De Freitas , Marc'Aurelio Ranzato , Yutian Chen

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…

Machine Learning · Computer Science 2019-10-29 Ruizhe Zhao , Brian Vogel , Tanvir Ahmed

Hyperparameter optimization (HPO) is concerned with the automated search for the most appropriate hyperparameter configuration (HPC) of a parameterized machine learning algorithm. A state-of-the-art HPO method is Hyperband, which, however,…

Machine Learning · Computer Science 2023-02-07 Jasmin Brandt , Marcel Wever , Dimitrios Iliadis , Viktor Bengs , Eyke Hüllermeier

Hyper-parameter optimization is crucial for pushing the accuracy of a deep learning model to its limits. A hyper-parameter optimization job, referred to as a study, involves numerous trials of training a model using different training…

Machine Learning · Computer Science 2020-06-23 Ahnjae Shin , Do Yoon Kim , Joo Seong Jeong , Byung-Gon Chun

Full-parameter fine-tuning has become the go-to choice for adapting language models (LMs) to downstream tasks due to its excellent performance. As LMs grow in size, fine-tuning the full parameters of LMs requires a prohibitively large…

Machine Learning · Computer Science 2024-06-18 Yongkang Liu , Yiqun Zhang , Qian Li , Tong Liu , Shi Feng , Daling Wang , Yifei Zhang , Hinrich Schütze

We consider a class of relaxation problems mixing slow and fast variations which can describe population dynamics models or hyperbolic systems, with varying stiffness (from non-stiff to strongly dissipative), and develop a multi-scale…

Analysis of PDEs · Mathematics 2020-05-27 Philippe Chartier , Mohammed Lemou , Léopold Trémant

The augmentation parameters matter to few-shot semantic segmentation since they directly affect the training outcome by feeding the networks with varying perturbated samples. However, searching optimal augmentation parameters for few-shot…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Quan Quan , Shang Zhao , Qingsong Yao , Heqin Zhu , S. Kevin Zhou

Large language models (LLMs) are increasingly prevalent across diverse applications. However, their enormous size limits storage and processing capabilities to a few well-resourced stakeholders. As a result, most applications rely on…

Computation and Language · Computer Science 2025-11-05 Mohammadsajad Alipour , Mohammad Mohammadi Amiri

Model pruning is a performance optimization technique for large language models like R1 or o3-mini. However, existing pruning methods often lead to significant performance degradation or require extensive retraining and fine-tuning. This…

Computation and Language · Computer Science 2025-05-21 Wei Jiang , Anying Fu , Youling Zhang

Hypernetworks, neural networks that predict the parameters of another neural network, are powerful models that have been successfully used in diverse applications from image generation to multi-task learning. Unfortunately, existing…

Machine Learning · Computer Science 2023-06-30 Jose Javier Gonzalez Ortiz , John Guttag , Adrian Dalca

Personalized Intelligence (PI) is the problem of providing customized AI experiences tailored to each individual user. In many applications, PI is preferred or even required. Existing personalization approaches involve fine-tuning…

Computation and Language · Computer Science 2022-03-15 Yiping Kang , Ashish Mahendra , Christopher Clarke , Lingjia Tang , Jason Mars

Accurate prediction of surface energies and stabilities is essential for materials design, yet first-principles calculations remain computationally expensive and most existing interatomic potentials are trained only on bulk systems. Here,…

Materials Science · Physics 2025-10-01 Jaekyun Hwang , Taehun Lee , Yonghyuk Lee , Su-Hyun Yoo
‹ Prev 1 3 4 5 6 7 10 Next ›