English
Related papers

Related papers: Enhancing LLM Training via Spectral Clipping

200 papers

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

Computation and Language · Computer Science 2024-10-10 Tao Meng , Ninareh Mehrabi , Palash Goyal , Anil Ramakrishna , Aram Galstyan , Richard Zemel , Kai-Wei Chang , Rahul Gupta , Charith Peris

Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficient at extreme scale. Although Adam remains the dominant optimizer for large-scale…

Machine Learning · Computer Science 2026-05-12 Aditya Ranganath

Spectral gradient descent (SpecGD) orthogonalizes the matrix parameter updates and has inspired practical optimizers such as Muon. They often perform well in large language model (LLM) training, but their dynamics remain poorly understood.…

Machine Learning · Computer Science 2026-02-09 Changmin Kang , Jihun Yun , Baekrok Shin , Yeseul Cho , Chulhee Yun

Adaptive optimizers with decoupled weight decay, such as AdamW, are the de facto standard for pre-training large transformer-based generative models. Yet the quadratic nature of the $\ell_2$ penalty embedded in weight decay drives all…

Machine Learning · Computer Science 2025-11-19 Fu-Ming Guo , Yingfang Fan

Large Language Models (LLMs) have shown immense potential in enhancing various aspects of our daily lives, from conversational AI to search and AI assistants. However, their growing capabilities come at the cost of extremely large model…

Machine Learning · Computer Science 2025-02-27 Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song , Yufa Zhou

We introduce Fiedler regularization, a novel approach for regularizing neural networks that utilizes spectral/graphical information. Existing regularization methods often focus on penalizing weights in a global/uniform manner that ignores…

Machine Learning · Statistics 2023-04-07 Edric Tam , David Dunson

Instruction tuning is a standard paradigm for adapting large language models (LLMs), but modern instruction datasets are large, noisy, and redundant, making full-data fine-tuning costly and often unnecessary. Existing data selection methods…

Computation and Language · Computer Science 2026-01-21 Zhihang Yuan , Chengyu Yue , Long Huang , Litu Ou , Lei Shi

Recent advances in pre-trained vision-language models have demonstrated remarkable zero-shot generalization capabilities. To further enhance these models' adaptability to various downstream tasks, prompt tuning has emerged as a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Yang Chen , Yanbin Wei , Ke Jin , Yi Kong , James Kwok , Yu Zhang

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing benchmarks. However, the escalating scale of model parameters imposes prohibitive memory overheads during training,…

Machine Learning · Computer Science 2026-04-28 Ziqing Wen , Ping Luo , Jiahuan Wang , Kun Yuan , Dongsheng Li , Tao Sun

Soft augmentation regularizes the supervised learning process of image classifiers by reducing label confidence of a training sample based on the magnitude of random-crop augmentation applied to it. This paper extends this adaptive label…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Georg Siedel , Ekagra Gupta , Weijia Shao , Silvia Vock , Andrey Morozov

The concept of learning to optimize involves utilizing a trainable optimization strategy rather than relying on manually defined full gradient estimations such as ADAM. We present a framework that jointly trains the full gradient estimator…

Machine Learning · Computer Science 2026-01-30 Ruiqi Wang , Diego Klabjan

The enhancement of spectrum efficiency and the realization of secure spectrum utilization are critically dependent on spectrum cognition. However, existing spectrum cognition methods often exhibit limited generalization and suboptimal…

Signal Processing · Electrical Eng. & Systems 2025-08-12 Chunyu Liu , Hao Zhang , Wei Wu , Fuhui Zhou , Qihui Wu , Derrick Wing Kwan Ng , Chan-Byoung Chae

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard…

Computation and Language · Computer Science 2024-05-31 Xudong Lu , Qi Liu , Yuhui Xu , Aojun Zhou , Siyuan Huang , Bo Zhang , Junchi Yan , Hongsheng Li

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

Computation and Language · Computer Science 2024-06-18 Tuc Nguyen , Thai Le

The ever-growing ecosystem of LLMs has posed a challenge in selecting the most appropriate pre-trained model to fine-tune amidst a sea of options. Given constrained resources, fine-tuning all models and making selections afterward is…

Machine Learning · Computer Science 2024-05-29 Haowei Lin , Baizhou Huang , Haotian Ye , Qinyu Chen , Zihao Wang , Sujian Li , Jianzhu Ma , Xiaojun Wan , James Zou , Yitao Liang

Spectral gradient methods, such as the Muon optimizer, modify gradient updates by preserving directional information while discarding scale, and have shown strong empirical performance in deep learning. We investigate the mechanisms…

Machine Learning · Statistics 2026-02-02 Guillaume Braun , Han Bao , Wei Huang , Masaaki Imaizumi

Muon has emerged as a strong competitor to AdamW for language model pre-training, yet its behavior at scale is sensitive to weight decay. Recent work has observed that, for Muon without decoupled weight decay, the spectral norm of weight…

Machine Learning · Computer Science 2026-05-12 Kai Lion , Florian Hübler , Bingcong Li , Antonio Orvieto , Niao He

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

Machine Learning · Computer Science 2025-10-31 Qiaoling Chen , Zijun Liu , Peng Sun , Shenggui Li , Guoteng Wang , Ziming Liu , Yonggang Wen , Siyuan Feng , Tianwei Zhang

Transformers consist of diverse building blocks, such as embedding layers, normalization layers, self-attention mechanisms, and point-wise feedforward networks. Thus, understanding the differences and interactions among these blocks is…

Machine Learning · Computer Science 2025-06-16 Jinbo Wang , Mingze Wang , Zhanpeng Zhou , Junchi Yan , Weinan E , Lei Wu