English
Related papers

Related papers: Autotuning PolyBench Benchmarks with LLVM Clang/Po…

200 papers

Optimizing the performance of GPU kernels is challenging for both human programmers and code generators. For example, CUDA programmers must set thread and block parameters for a kernel, but might not have the intuition to make a good…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-06-30 Robert V. Lim , Boyana Norris , Allen D. Malony

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

Machine Learning · Computer Science 2024-06-18 Jiahan Zhang , Qi Wei , Feng Liu , Lei Feng

Supervised fine-tuning is the most common method to adapt large language models (LLMs) to downstream tasks, but full fine-tuning LLMs requires massive computational resources. Recently, parameter-efficient fine-tuning (PEFT) methods have…

Computation and Language · Computer Science 2024-02-27 Xiangdi Meng , Damai Dai , Weiyao Luo , Zhe Yang , Shaoxiang Wu , Xiaochen Wang , Peiyi Wang , Qingxiu Dong , Liang Chen , Zhifang Sui

With the impact of real-time processing being realized in the recent past, the need for efficient implementations of reinforcement learning algorithms has been on the rise. Albeit the numerous advantages of Bellman equations utilized in RL…

Machine Learning · Computer Science 2023-03-15 Saumil Shivdikar , Jagannath Nirmal

Fine-tuning large language models (LLMs) with parameter-efficient techniques such as LoRA and QLoRA has enabled adaptation of foundation models on modest hardware. Yet the efficiency of such training on consumer-grade GPUs, especially under…

Machine Learning · Computer Science 2025-09-17 MSR Avinash

The closed-loop performance of model predictive controllers (MPCs) is sensitive to the choice of prediction models, controller formulation, and tuning parameters. However, prediction models are typically optimized for prediction accuracy…

Systems and Control · Electrical Eng. & Systems 2020-11-25 Farshud Sorourifar , Georgios Makrygirgos , Ali Mesbah , Joel A. Paulson

The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all candidates due to computational constraints. Despite the recent…

Machine Learning · Computer Science 2025-06-03 Xinyue Zeng , Haohui Wang , Junhong Lin , Jun Wu , Tyler Cody , Dawei Zhou

Algebraic Multigrid (AMG) is one of the most used iterative algorithms for solving large sparse linear equations $Ax=b$. In AMG, the coarse grid is a key component that affects the efficiency of the algorithm, the construction of which…

Numerical Analysis · Mathematics 2023-08-17 Haifeng Zou , Xiaowen Xu , Chen-Song Zhang , Zeyao Mo

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperparameter choices,…

Bayesian optimization provides an effective method to optimize expensive-to-evaluate black box functions. It has been widely applied to problems in many fields, including notably in computer science, e.g. in machine learning to optimize…

Machine Learning · Computer Science 2025-11-18 Mike Diessner , Joseph O'Connor , Andrew Wynn , Sylvain Laizet , Yu Guan , Kevin Wilson , Richard D. Whalley

The polyhedral model provides a powerful mathematical abstraction to enable effective optimization of loop nests with respect to a given optimization goal, e.g., exploiting parallelism. Unexploited reduction properties are a frequent reason…

Programming Languages · Computer Science 2015-05-29 Johannes Doerfert , Kevin Streit , Sebastian Hack , Zino Benaissa

We introduce a sequential learning algorithm to address a robust controller tuning problem, which in effect, finds (with high probability) a candidate solution satisfying the internal performance constraint to a chance-constrained program…

Optimization and Control · Mathematics 2021-10-19 Robert Chin , Chris Manzie , Iman Shames , Dragan Nešić , Jonathan E. Rowe

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Computation and Language · Computer Science 2022-05-03 Shoujie Tong , Qingxiu Dong , Damai Dai , Yifan song , Tianyu Liu , Baobao Chang , Zhifang Sui

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings the best of…

Machine Learning · Computer Science 2021-04-27 Lucas Zimmer , Marius Lindauer , Frank Hutter

Bayesian Optimization (BO) has become a core method for solving expensive black-box optimization problems. While much research focussed on the choice of the acquisition function, we focus on online length-scale adaption and the choice of…

Machine Learning · Computer Science 2016-12-12 Kim Peter Wabersich , Marc Toussaint

Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of tasks. Nonetheless, this technique often necessitates substantial computational resources, making it impractical for deployment…

Computation and Language · Computer Science 2024-10-08 Zhenting Qi , Xiaoyu Tan , Shaojie Shi , Chao Qu , Yinghui Xu , Yuan Qi

Kernel-based nonparametric models have become very attractive for model-based control approaches for nonlinear systems. However, the selection of the kernel and its hyperparameters strongly influences the quality of the learned model.…

Systems and Control · Electrical Eng. & Systems 2019-09-13 Thomas Beckers , Somil Bansal , Claire J. Tomlin , Sandra Hirche

Fine-tuning Large Language Models (LLMs) is an effective method to enhance their performance on downstream tasks. However, choosing the appropriate setting of tuning hyperparameters (HPs) is a labor-intensive and computationally expensive…

In this work, we address the problem of tuning communication libraries by using a deep reinforcement learning approach. Reinforcement learning is a machine learning technique incredibly effective in solving game-like situations. In fact,…

Machine Learning · Computer Science 2019-09-16 Alessandro Fanfarillo , Davide Del Vento

Clinical prognostic models derived from largescale healthcare data can inform critical diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) in prognostic research, we developed AUTOPROGNOSIS: a system…

Machine Learning · Computer Science 2018-02-21 Ahmed M. Alaa , Mihaela van der Schaar
‹ Prev 1 3 4 5 6 7 10 Next ›