English
Related papers

Related papers: AdaFish: Fast low-rank parameter-efficient fine-tu…

200 papers

The estimation of continuous parameters from measured data plays a central role in many fields of physics. A key tool in understanding and improving such estimation processes is the concept of Fisher information, which quantifies how…

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 present differentiable particle filters (DPFs): a differentiable implementation of the particle filter algorithm with learnable motion and measurement models. Since DPFs are end-to-end differentiable, we can efficiently train their…

Machine Learning · Computer Science 2018-05-31 Rico Jonschkowski , Divyam Rastogi , Oliver Brock

FISH is a fast and simple ideal magneto-hydrodynamics code that scales to ~10 000 processes for a Cartesian computational domain of ~1000^3 cells. The simplicity of FISH has been achieved by the rigorous application of the operator…

Instrumentation and Methods for Astrophysics · Physics 2011-08-11 R. Kaeppeli , S. C. Whitehouse , S. Scheidegger , U. -L. Pen , M. Liebendoerfer

Large language model-based agents have recently emerged as powerful approaches for solving dynamic and multi-step tasks. Most existing agents employ planning mechanisms to guide long-term actions in dynamic environments. However, current…

Artificial Intelligence · Computer Science 2026-04-28 Haoran Tan , Zeyu Zhang , Chen Ma , Tianze Liu , Quanyu Dai , Xu Chen

In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Ningyuan Tang , Minghao Fu , Ke Zhu , Jianxin Wu

Pre-training and fine-tuning have achieved significant advances in the information retrieval (IR). A typical approach is to fine-tune all the parameters of large-scale pre-trained models (PTMs) on downstream tasks. As the model size and the…

Information Retrieval · Computer Science 2022-08-23 Xinyu Ma , Jiafeng Guo , Ruqing Zhang , Yixing Fan , Xueqi Cheng

We propose a new algorithm for efficiently solving the damped Fisher matrix in large-scale scenarios where the number of parameters significantly exceeds the number of available samples. This problem is fundamental for natural gradient…

Machine Learning · Computer Science 2023-10-27 Yixiao Chen , Hao Xie , Han Wang

Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence. However, the wide range of tasks and high computational costs make full fine-tuning impractical. To overcome this,…

Machine Learning · Computer Science 2025-06-27 Chongjie Si , Zhiyi Shi , Xuehui Wang , Yichen Xiao , Xiaokang Yang , Wei Shen

Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is $\alpha$-entmax attention, a differentiable sparse alternative to…

Machine Learning · Computer Science 2026-04-17 Nuno Gonçalves , Hugo Pitorro , Vlad Niculae , Edoardo Ponti , Lei Li , Andre Martins , Marcos Treviso

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by…

Computation and Language · Computer Science 2022-11-04 Haojie Zhang , Ge Li , Jia Li , Zhongjin Zhang , Yuqi Zhu , Zhi Jin

Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's…

Machine Learning · Computer Science 2020-05-06 Wenjie Li , Zhaoyang Zhang , Xinjiang Wang , Ping Luo

We study adaptive (or online) nonlinear regression with Long-Short-Term-Memory (LSTM) based networks, i.e., LSTM-based adaptive learning. In this context, we introduce an efficient Extended Kalman filter (EKF) based second-order training…

Machine Learning · Computer Science 2021-06-01 N. Mert Vural , Salih Ergüt , Suleyman S. Kozat

As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data…

Machine Learning · Computer Science 2024-10-21 Ji Liu , Jiaxiang Ren , Ruoming Jin , Zijie Zhang , Yang Zhou , Patrick Valduriez , Dejing Dou

Adaptive stochastic gradient methods such as AdaGrad have gained popularity in particular for training deep neural networks. The most commonly used and studied variant maintains a diagonal matrix approximation to second order information by…

A large-scale recommender system usually consists of recall and ranking modules. The goal of ranking modules (aka rankers) is to elaborately discriminate users' preference on item candidates proposed by recall modules. With the success of…

Information Retrieval · Computer Science 2022-05-24 Xinyan Fan , Jianxun Lian , Wayne Xin Zhao , Zheng Liu , Chaozhuo Li , Xing Xie

Recently, Factorization Machines (FM) has become more and more popular for recommendation systems, due to its effectiveness in finding informative interactions between features. Usually, the weights for the interactions is learnt as a low…

Machine Learning · Computer Science 2018-04-18 Longfei Li , Peilin Zhao , Jun Zhou , Xiaolong Li

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

Machine Learning · Computer Science 2025-05-22 Rohan Deb , Kiran Thekumparampil , Kousha Kalantari , Gaurush Hiranandani , Shoham Sabach , Branislav Kveton

For several decades, image restoration remains an active research topic in low-level computer vision and hence new approaches are constantly emerging. However, many recently proposed algorithms achieve state-of-the-art performance only at…

Computer Vision and Pattern Recognition · Computer Science 2015-03-26 Yunjin Chen , Wei Yu , Thomas Pock

The overfitting is one of the cursing subjects in the deep learning field. To solve this challenge, many approaches were proposed to regularize the learning models. They add some hyper-parameters to the model to extend the generalization;…

Machine Learning · Computer Science 2020-05-06 Mohammad Mahdi Bejani , Mehdi Ghatee