English
Related papers

Related papers: On the Duality between Gradient Transformations an…

200 papers

Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimization on Riemannian manifolds. However, existing Riemannian…

Machine Learning · Computer Science 2025-02-07 Peilin Yu , Yuwei Wu , Zhi Gao , Xiaomeng Fan , Yunde Jia

Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us to rethink generalization by bringing forth new phenomena,…

Machine Learning · Statistics 2020-12-01 Vatsal Shah , Soumya Basu , Anastasios Kyrillidis , Sujay Sanghavi

Adapters have become a widely adopted strategy for efficient fine-tuning of large pretrained models, particularly in resource-constrained settings. However, their performance under extreme data scarcity, common in medical imaging due to…

Computational Engineering, Finance, and Science · Computer Science 2026-02-24 Ziquan Zhu , Hanruo Zhu , Siyuan Lu , Xiang Li , Yanda Meng , Gaojie Jin , Lu Yin , Lijie Hu , Di Wang , Lu Liu , Tianjin Huang

Adapters are widely popular parameter-efficient transfer learning approaches in natural language processing that insert trainable modules in between layers of a pre-trained language model. Apart from several heuristics, however, there has…

Computation and Language · Computer Science 2023-10-31 Rishabh Bhardwaj , Tushar Vaidya , Soujanya Poria

Training large language models (LLMs) is often bottlenecked by extreme memory demands, with optimizer states dominating the footprint. Recent works mitigates this cost by projecting gradients into low-dimensional subspaces using…

Machine Learning · Computer Science 2025-10-03 Sahar Rajabi , Nayeema Nonta , Samanvay Vajpayee , Sirisha Rambhatla

Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models. Despite its computational efficiency, LoRA still yields inferior performance compared to full fine-tuning.…

Machine Learning · Computer Science 2025-03-25 Zhengbo Wang , Jian Liang , Ran He , Zilei Wang , Tieniu Tan

In the training of large language models, parameter-efficient techniques such as LoRA optimize memory usage and reduce communication overhead and memory usage during the fine-tuning phase. However, applying such techniques directly during…

Machine Learning · Computer Science 2025-01-03 Kaiye Zhou , Shucheng Wang , Jun Xu

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…

Machine Learning · Computer Science 2013-03-12 Tommi Vatanen , Tapani Raiko , Harri Valpola , Yann LeCun

Efficient estimation of high-dimensional matrices-including covariance and precision matrices-is a cornerstone of modern multivariate statistics. Most existing studies have focused primarily on the theoretical properties of the estimators…

Machine Learning · Computer Science 2026-03-31 Wan Tian , Hui Yang , Zhouhui Lian , Lingyue Zhang , Yijie Peng

The well-designed structures in neural networks reflect the prior knowledge incorporated into the models. However, though different models have various priors, we are used to training them with model-agnostic optimizers such as SGD. In this…

Machine Learning · Computer Science 2023-02-10 Xiaohan Ding , Honghao Chen , Xiangyu Zhang , Kaiqi Huang , Jungong Han , Guiguang Ding

Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual learning (CL) to update models online, enabling adaptation to new tasks while preserving…

Machine Learning · Computer Science 2025-06-13 Yu-Yang Qian , Yuan-Ze Xu , Zhen-Yu Zhang , Peng Zhao , Zhi-Hua Zhou

Parameter-Efficient Fine-Tuning (PEFT) has become the standard for adapting large language models (LLMs). In this work we challenge the wide-spread assumption that parameter efficiency equates memory efficiency and on-device adaptability.…

Machine Learning · Computer Science 2026-04-28 Irene Tenison , Stella Ahn , Miriam Kim , Ebtisam Alshehri , Lalana Kagal

Over the past years, there has been significant interest in understanding the implicit bias of gradient descent optimization and its connection to the generalization properties of overparametrized neural networks. Several works observed…

Optimization and Control · Mathematics 2025-03-11 Hung-Hsu Chou , Johannes Maly , Claudio Mayrink Verdun , Bernardo Freitas Paulo da Costa , Heudson Mirandola

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Machine Learning · Computer Science 2018-04-13 Noam Shazeer , Mitchell Stern

Several recent works demonstrate that transformers can implement algorithms like gradient descent. By a careful construction of weights, these works show that multiple layers of transformers are expressive enough to simulate iterations of…

Machine Learning · Computer Science 2023-11-13 Kwangjun Ahn , Xiang Cheng , Hadi Daneshmand , Suvrit Sra

We show that memory-augmented Transformers can implement the entire class of linear first-order methods (LFOMs), a class that contains gradient descent (GD) and more advanced methods such as conjugate gradient descent (CGD), momentum…

Machine Learning · Computer Science 2025-02-04 Sanchayan Dutta , Suvrit Sra

Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprisingly complex as they depend on several hyperparameters such as…

Machine Learning · Computer Science 2026-02-09 Nan Chen , Soledad Villar , Soufiane Hayou

Fine-tuning techniques based on Large Pretrained Language Models (LPLMs) have been proven to significantly enhance model performance on a variety of downstream tasks and effectively control the output behaviors of LPLMs. Recent studies have…

Computation and Language · Computer Science 2024-04-02 Yao Liang , Yuwei Wang , Yang Li , Yi Zeng

The rapid growth of large models has raised concerns about their environmental impact and equity in accessibility due to significant computational costs. Low-Rank Adapters (LoRA) offer a lightweight solution for finetuning large models,…

Machine Learning · Computer Science 2026-02-06 Prakhar Kaushik , Ankit Vaidya , Shravan Chaudhari , Alan Yuille