English
Related papers

Related papers: Greedy-Gnorm: A Gradient Matrix Norm-Based Alterna…

200 papers

Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal…

Machine Learning · Statistics 2026-05-19 Naman Agarwal , Siddhartha R. Dalal , Vishal Misra

In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware pruning methods attempt to selectively discard redundant tokens, they largely rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Mingzhe Huang , Weijun Wang , Xin Ding , Liang Mi , Hao Wen , Yuanchun Li , Lichen Pang , Shansong Yang , Yunxin Liu , Ting Cao

Recent years have seen a growing adoption of Transformer models such as BERT in Natural Language Processing and even in Computer Vision. However, due to their size, there has been limited adoption of such models within resource-constrained…

Computation and Language · Computer Science 2021-11-18 Archit Parnami , Rahul Singh , Tarun Joshi

Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate functionally relevant reasoning. Prior work on compact…

Computation and Language · Computer Science 2026-04-22 Janvijay Singh , Dilek Hakkani-Tür

Fine-tuning transformer models after unsupervised pre-training reaches a very high performance on many different natural language processing tasks. Unfortunately, transformers suffer from long inference times which greatly increases costs…

Computation and Language · Computer Science 2022-03-30 David Peer , Sebastian Stabinger , Stefan Engl , Antonio Rodriguez-Sanchez

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Computation and Language · Computer Science 2022-04-08 Zuzana Jelčicová , Marian Verhelst

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead…

Computation and Language · Computer Science 2021-10-08 Kyuhong Shim , Iksoo Choi , Wonyong Sung , Jungwook Choi

Symbolic regression aims to derive interpretable symbolic expressions from data in order to better understand and interpret data. %which plays an important role in knowledge discovery and interpretable machine learning. In this study, a…

Machine Learning · Computer Science 2024-01-30 Min Wu , Weijun Li , Lina Yu , Wenqiang Li , Jingyi Liu , Yanjie Li , Meilan Hao

Global Neuron Importance Estimation is used to prune neural networks for efficiency reasons. To determine the global importance of each neuron or convolutional kernel, most of the existing methods either use activation or gradient…

Machine Learning · Computer Science 2023-11-01 Suman Sapkota , Binod Bhattarai

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Computation and Language · Computer Science 2026-01-28 Songtao Liu , Peng Liu

Auto-regressive large language models such as GPT-3 require enormous computational resources to use. Traditionally, structured pruning methods are employed to reduce resource usage. However, their application to and efficacy for generative…

Computation and Language · Computer Science 2023-02-09 Michael Santacroce , Zixin Wen , Yelong Shen , Yuanzhi Li

Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit…

Computation and Language · Computer Science 2026-04-10 Kaiyuan Tian , Yu Tang , Gongqingjian Jiang , Baihui Liu , Yifu Gao , Xialin Su , Linbo Qiao , Dongsheng Li

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Yuki Igaue , Hiroaki Aizawa

As language models have grown in parameters and layers, it has become much harder to train and infer with them on single GPUs. This is severely restricting the availability of large language models such as GPT-3, BERT-Large, and many…

Computation and Language · Computer Science 2022-12-29 Jasdeep Singh Grover , Bhavesh Gawri , Ruskin Raj Manku

Training high-quality deep models necessitates vast amounts of data, resulting in overwhelming computational and memory demands. Recently, data pruning, distillation, and coreset selection have been developed to streamline data volume by…

Machine Learning · Computer Science 2024-10-18 Guibin Zhang , Haonan Dong , Yuchen Zhang , Zhixun Li , Dingshuo Chen , Kai Wang , Tianlong Chen , Yuxuan Liang , Dawei Cheng , Kun Wang

To reduce computational overhead while maintaining model performance, model pruning techniques have been proposed. Among these, structured pruning, which removes entire convolutional channels or layers, significantly enhances computational…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Qingsong Lv , Jiasheng Sun , Sheng Zhou , Xu Zhang , Liangcheng Li , Yun Gao , Sun Qiao , Jie Song , Jiajun Bu

Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under linear function approximation and Markovian sampling, and the algorithm is shown…

Machine Learning · Computer Science 2021-03-31 Shaocong Ma , Ziyi Chen , Yi Zhou , Shaofeng Zou

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

Machine Learning · Computer Science 2020-10-13 Sai Aparna Aketi , Sourjya Roy , Anand Raghunathan , Kaushik Roy

Recently, a race towards the simplification of deep networks has begun, showing that it is effectively possible to reduce the size of these models with minimal or no performance loss. However, there is a general lack in understanding why…

Machine Learning · Computer Science 2022-12-29 Enzo Tartaglione , Andrea Bragagnolo , Marco Grangetto

Orthogonal greedy learning (OGL) is a stepwise learning scheme that adds a new atom from a dictionary via the steepest gradient descent and build the estimator via orthogonal projecting the target function to the space spanned by the…

Machine Learning · Computer Science 2014-11-14 Lin Xu , Shaobo Lin , Jinshan Zeng , Zongben Xu