English
Related papers

Related papers: Anytime Training with Schedule-Free Spectral Optim…

200 papers

In many optimization problems in wireless communications, the expressions of objective function or constraints are hard or even impossible to derive, which makes the solutions difficult to find. In this paper, we propose a model-free…

Machine Learning · Computer Science 2019-07-31 Chengjian Sun , Dong Liu , Chenyang Yang

Spiking Neural Networks (SNNs) that operate in an event-driven manner and employ binary spike representation have recently emerged as promising candidates for energy-efficient computing. However, a cost bottleneck arises in obtaining…

Neural and Evolutionary Computing · Computer Science 2024-01-22 Yunpeng Yao , Man Wu , Zheng Chen , Renyuan Zhang

Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; however, current parameter-efficient fine-tuning (PEFT) methods remain largely limited to single-task adaptation. We introduce \textbf{Free…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Shih-Wen Liu , Yen-Chang Chen , Wei-Ta Chu , Fu-En Yang , Yu-Chiang Frank Wang

Time series forecasting plays a pivotal role in a wide range of applications, including weather prediction, healthcare, structural health monitoring, predictive maintenance, energy systems, and financial markets. While models such as LSTM,…

Machine Learning · Computer Science 2026-04-03 Qianying Cao , Shanqing Liu , Alan John Varghese , Jerome Darbon , Michael Triantafyllou , George Em Karniadakis

Large Language Models (LLMs) achieve competitive performance across diverse natural language processing (NLP) tasks, yet pretraining is computationally demanding, making optimizer efficiency an important practical consideration. Muon…

Machine Learning · Computer Science 2026-01-22 Jingru Li , Yibo Fan , Huan Li

We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to performing domain adaptation on an unlabeled target domain without any access to source data; the available…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Björn Michele , Alexandre Boulch , Tuan-Hung Vu , Gilles Puy , Renaud Marlet , Nicolas Courty

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent…

Machine Learning · Computer Science 2018-11-20 Farzan Farnia , Jesse M. Zhang , David Tse

Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks. Despite many advantages, neural fields often have a high training cost, which prevents a broader adoption. In this paper,…

Machine Learning · Computer Science 2026-02-04 Taesun Yeom , Sangyoon Lee , Jaeho Lee

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

In recent studies, line search methods have been demonstrated to significantly enhance the performance of conventional stochastic gradient descent techniques across various datasets and architectures, while making an otherwise critical…

Machine Learning · Computer Science 2024-07-31 Philip Kenneweg , Tristan Kenneweg , Fabian Fumagalli , Barbara Hammer

Recently, vision-based Advanced Driver Assist Systems have gained broad interest. In this work, we investigate free-space detection, for which we propose to employ a Fully Convolutional Network (FCN). We show that this FCN can be trained in…

Computer Vision and Pattern Recognition · Computer Science 2017-01-06 Willem P. Sanberg , Gijs Dubbelman , Peter H. N. de With

Deep neural networks (DNNs) have shown their success as high-dimensional function approximators in many applications; however, training DNNs can be challenging in general. DNN training is commonly phrased as a stochastic optimization…

Machine Learning · Computer Science 2021-09-30 Elizabeth Newman , Julianne Chung , Matthias Chung , Lars Ruthotto

Both full fine-tuning (Full FT) and parameter-efficient fine-tuning methods such as LoRA introduce weight updates without accounting for the spectral structure established during pretraining. As a result, noisy gradients from limited…

Machine Learning · Computer Science 2026-05-25 Yequan Zhao , Ruijie Zhang , Liyan Tan , Niall Moran , Tong Qin , Zheng Zhang

Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Dongze Lian , Daquan Zhou , Jiashi Feng , Xinchao Wang

The training of deep vision models is fundamentally a signal recovery problem amidst high-dimensional stochastic noise. Current optimization paradigms impose a static compromise on information channel capacity. For instance, magnitude-based…

Machine Learning · Computer Science 2025-12-03 Ahmed Nebli

Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gradient splitting, but its static hyperparameters -- the subspace ratio ($\rho$) and update…

Machine Learning · Computer Science 2026-04-30 Quang-Hung Bui , Anh Son Ta

This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw…

Machine Learning · Computer Science 2020-10-22 Sebastian Pokutta , Christoph Spiegel , Max Zimmer

Distributed optimization is essential for training large models on large datasets. Multiple approaches have been proposed to reduce the communication overhead in distributed training, such as synchronizing only after performing multiple…

Machine Learning · Computer Science 2020-02-21 Jianyu Wang , Vinayak Tantia , Nicolas Ballas , Michael Rabbat

Recent trends towards training ever-larger language models have substantially improved machine learning performance across linguistic tasks. However, the huge cost of training larger models can make tuning them prohibitively expensive,…

Computation and Language · Computer Science 2022-09-13 Jared Lichtarge , Chris Alberti , Shankar Kumar

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi