English
Related papers

Related papers: Memory-Efficient Structured Backpropagation for On…

200 papers

Fine-tuning large language models (LLMs) with zeroth-order (ZO) optimization reduces memory by approximating gradients through function evaluations. However, existing methods essentially perform updates in a one-dimensional space, and…

Machine Learning · Computer Science 2026-01-19 Jian Feng , Zhihong Huang

The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, semi-structured sparsity offers a promising solution by strategically retaining $N$ elements…

Machine Learning · Computer Science 2026-05-14 Yan Sun , Qixin Zhang , Zhiyuan Yu , Xikun Zhang , Li Shen , Dacheng Tao

Despite its importance for federated learning, continuous learning and many other applications, on-device training remains an open problem for EdgeAI. The problem stems from the large number of operations (e.g., floating point…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Yuedong Yang , Guihong Li , Radu Marculescu

Structural pruning techniques are essential for deploying multimodal large language models (MLLMs) across various hardware platforms, from edge devices to cloud servers. However, current pruning methods typically determine optimal…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Zhihan Zhang , Xiang Pan , Hongchen Wei , Zhenzhong Chen

Self-attention is a key enabler of state-of-art accuracy for various transformer-based Natural Language Processing models. This attention mechanism calculates a correlation score for each word with respect to the other words in a sentence.…

Computation and Language · Computer Science 2022-04-18 Zheng Li , Soroush Ghodrati , Amir Yazdanbakhsh , Hadi Esmaeilzadeh , Mingu Kang

Zeroth-Order (ZO) optimization has emerged as a promising solution for fine-tuning LLMs under strict memory constraints, as it avoids the prohibitive memory cost of storing activations for backpropagation. However, existing ZO methods…

Machine Learning · Computer Science 2026-05-25 Wei Lin , Yining Jiang , Qingyu Song , Qiao Xiang , Hong Xu

State-of-the-art models are now trained with billions of parameters, reaching hardware limits in terms of memory consumption. This has created a recent demand for memory-efficient optimizers. To this end, we investigate the limits and…

Machine Learning · Computer Science 2019-02-14 Xinyi Chen , Naman Agarwal , Elad Hazan , Cyril Zhang , Yi Zhang

Quantization has emerged as a mainstream approach for deploying Large Language Models (LLMs) on resource-constrained devices, yet compressing precision below 4-bit typically causes severe performance degradation or prohibitive retraining…

Machine Learning · Computer Science 2026-05-22 Shu-Hao Zhang , Le-Tong Huang , Xiang-Sheng Deng , Xin-Yi Zou , Chen Wu , Nan Li , Shao-Qun Zhang , Zhi-Hua Zhou

This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Inverted Residual Block (IRB) serves as the infrastructure for lightweight CNNs, but no…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Jiangning Zhang , Xiangtai Li , Jian Li , Liang Liu , Zhucun Xue , Boshen Zhang , Zhengkai Jiang , Tianxin Huang , Yabiao Wang , Chengjie Wang

Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer…

Machine Learning · Computer Science 2024-06-26 Aashiq Muhamed , Oscar Li , David Woodruff , Mona Diab , Virginia Smith

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Machine Learning · Computer Science 2025-04-29 Xilong Xie , Liang Wang , Limin Xiao , Meng Han , Lin Sun , Shuai Zheng , Xiangrong Xu

Gradient orthogonalization is a simple strategy that shows great utility in speeding up gradient descent. The Muon optimizer (Jordan, Jin, et al., 2024) combines gradient orthogonalization with first-order momentum and achieves significant…

Machine Learning · Computer Science 2025-10-21 Ahmed Khaled , Kaan Ozkara , Tao Yu , Mingyi Hong , Youngsuk Park

Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an…

Machine Learning · Computer Science 2018-06-05 Maohua Zhu , Jason Clemons , Jeff Pool , Minsoo Rhu , Stephen W. Keckler , Yuan Xie

With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the inherently personal and context-dependent nature of…

Computation and Language · Computer Science 2026-05-19 Changmin Lee , Jaemin Kim , Taesik Gong

Differentially Private (DP) learning has seen limited success for building large deep learning models of text, and straightforward attempts at applying Differentially Private Stochastic Gradient Descent (DP-SGD) to NLP tasks have resulted…

Machine Learning · Computer Science 2022-11-11 Xuechen Li , Florian Tramèr , Percy Liang , Tatsunori Hashimoto

Fine-tuning Large Language Models (LLMs) is a common practice to adapt pre-trained models for specific applications. While methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls…

Computation and Language · Computer Science 2024-07-23 Dengchun Li , Yingzi Ma , Naizheng Wang , Zhengmao Ye , Zhiyuan Cheng , Yinghao Tang , Yan Zhang , Lei Duan , Jie Zuo , Cal Yang , Mingjie Tang

Parameter-efficient fine-tuning (PEFT), particularly Low-Rank Adaptation (LoRA), adapts large language models (LLMs) by training only a small fraction of parameters. However, as the rank of the low-rank matrices used for adaptation…

Computation and Language · Computer Science 2025-09-29 Yupeng Chang , Chenlu Guo , Yi Chang , Yuan Wu

We consider multi-value expansion planning (MEP), a general bilevel optimization model in which a planner optimizes arbitrary functions of the dispatch outcome in the presence of a partially controllable, competitive electricity market. The…

Optimization and Control · Mathematics 2024-04-02 Anthony Degleris , Abbas El Gamal , Ram Rajagopal

Critical aspects of computational imaging systems, such as experimental design and image priors, can be optimized through deep networks formed by the unrolled iterations of classical model-based reconstructions (termed physics-based…

Computer Vision and Pattern Recognition · Computer Science 2020-03-13 Michael Kellman , Kevin Zhang , Jon Tamir , Emrah Bostan , Michael Lustig , Laura Waller

With the proliferation of mobile devices, the need for an efficient model to restore any degraded image has become increasingly significant and impactful. Traditional approaches typically involve training dedicated models for each specific…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Bin Ren , Eduard Zamfir , Zongwei Wu , Yawei Li , Yidi Li , Danda Pani Paudel , Radu Timofte , Ming-Hsuan Yang , Nicu Sebe