English
Related papers

Related papers: Batch Loss Score for Dynamic Data Pruning

200 papers

With the rapid advancement of large language models , code generation has become a key benchmark for evaluating LLM capabilities. However, existing benchmarks face two major challenges: (1) the escalating cost of constructing high-quality…

Artificial Intelligence · Computer Science 2025-08-05 Junjie Shi , Wei Ma , Shi Ying , Lingxiao Jiang , Yang liu , Bo Du

Choosing appropriate step sizes is critical for reducing the computational cost of training large-scale neural network models. Mini-batch sub-sampling (MBSS) is often employed for computational tractability. However, MBSS introduces a…

Machine Learning · Statistics 2019-09-17 Younghwan Chae , Daniel N. Wilke

We study acquisition functions for active learning (AL) for text classification. The Expected Loss Reduction (ELR) method focuses on a Bayesian estimate of the reduction in classification error, recently updated with Mean Objective Cost of…

Machine Learning · Computer Science 2021-10-28 Wei Tan , Lan Du , Wray Buntine

In high-dimensional statistics, the Lasso is a cornerstone method for simultaneous variable selection and parameter estimation. However, its reliance on the squared loss function renders it highly sensitive to outliers and heavy-tailed…

Machine Learning · Statistics 2025-11-20 The Tien Mai

Bayesian neural networks (BNNs) provide a formalism to quantify and calibrate uncertainty in deep learning. Current inference approaches for BNNs often resort to few-sample estimation for scalability, which can harm predictive performance,…

Machine Learning · Computer Science 2024-02-14 Zhe Zeng , Guy Van den Broeck

The deep-learning-based least squares method has shown successful results in solving high-dimensional non-linear partial differential equations (PDEs). However, this method usually converges slowly. To speed up the convergence of this…

Numerical Analysis · Mathematics 2025-07-10 Wenhan Gao , Chunmei Wang

Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an…

Machine Learning · Computer Science 2020-02-21 Yeming Wen , Dustin Tran , Jimmy Ba

Data subset selection aims to find a smaller yet informative subset of a large dataset that can approximate the full-dataset training, addressing challenges associated with training neural networks on large-scale datasets. However, existing…

Machine Learning · Computer Science 2024-06-06 Hoyong Choi , Nohyun Ki , Hye Won Chung

Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected…

Machine Learning · Computer Science 2024-03-28 Ao Zhou , Bin Liu , Jin Wang , Grigorios Tsoumakas

Estimating time-frequency domain masks for single-channel speech enhancement using deep learning methods has recently become a popular research field with promising results. In this paper, we propose a novel components loss (CL) for the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-15 Ziyi Xu , Samy Elshamy , Ziyue Zhao , Tim Fingscheidt

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Computation and Language · Computer Science 2025-06-04 Yuli Chen , Bo Cheng , Jiale Han , Yingying Zhang , Yingting Li , Shuhao Zhang

Study samples often differ from the target populations of inference and policy decisions in non-random ways. Researchers typically believe that such departures from random sampling -- due to changes in the population over time and space, or…

Methodology · Statistics 2023-07-20 Tamara Broderick , Ryan Giordano , Rachael Meager

Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained on the full dataset. However, the expanding body of research…

Computation and Language · Computer Science 2025-02-25 Ziche Liu , Rui Ke , Yajiao Liu , Feng Jiang , Haizhou Li

Implicit feedback, often used to build recommender systems, unavoidably confronts noise due to factors such as misclicks and position bias. Previous studies have attempted to alleviate this by identifying noisy samples based on their…

Information Retrieval · Computer Science 2024-09-17 Tianrui Song , Wenshuo Chao , Hao Liu

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ…

Machine Learning · Computer Science 2018-12-18 Sam McCandlish , Jared Kaplan , Dario Amodei , OpenAI Dota Team

The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the increasing computational cost is becoming unaffordable. In this…

Machine Learning · Computer Science 2024-06-17 Muyang He , Shuo Yang , Tiejun Huang , Bo Zhao

Compute-efficient training of language models has become an important issue. We consider data pruning for data-efficient training of LLMs. In this work, we consider a data pruning method based on information entropy. We propose that the…

Artificial Intelligence · Computer Science 2024-12-13 Minsang Kim , Seungjun Baek

Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and…

Machine Learning · Computer Science 2023-08-04 Ruixuan Xiao , Yiwen Dong , Haobo Wang , Lei Feng , Runze Wu , Gang Chen , Junbo Zhao

The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched…

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning. In this paper,…

Machine Learning · Computer Science 2017-09-14 Angelos Katharopoulos , François Fleuret
‹ Prev 1 3 4 5 6 7 10 Next ›