English
Related papers

Related papers: Training LLMs with MXFP4

200 papers

We introduce Model Feedback Learning (MFL), a novel test-time optimization framework for optimizing inputs to pre-trained AI models or deployed hardware systems without requiring any retraining of the models or modifications to the…

Machine Learning · Computer Science 2025-05-23 Shangding Gu , Donghao Ying , Ming Jin , Yu Joe Lu , Jun Wang , Javad Lavaei , Costas Spanos

It is well known that selecting samples with large losses/gradients can significantly reduce the number of training steps. However, the selection overhead is often too high to yield any meaningful gains in terms of overall training time. In…

Machine Learning · Computer Science 2025-06-05 Rudrajit Das , Xi Chen , Bertram Ieong , Parikshit Bansal , Sujay Sanghavi

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs. Yet, existing quantized training methods still…

Machine Learning · Computer Science 2026-02-02 Andrei Panferov , Erik Schultheis , Soroush Tabesh , Dan Alistarh

Machine-learning interatomic potentials (MLIPs) such as neuroevolution potentials (NEP) combine quantum-mechanical accuracy with computational efficiency significantly accelerate atomistic dynamic simulations. Trained by derivative-free…

Disordered Systems and Neural Networks · Physics 2026-04-14 Hongfu Huang , Junhao Peng , Kaiqi Li , Jian Zhou , Zhimei Sun

We present a mixed-precision benchmark called HPL-MxP that uses both a lower-precision LU factorization with a non-stationary iterative refinement based on GMRES. We evaluate the numerical stability of one of the methods of generating the…

Numerical Analysis · Mathematics 2025-09-25 Jack Dongarra , Piotr Luszczek

Federated Learning (FL) facilitates decentralized collaborative learning without transmitting raw data. However, reliance on fixed global rounds or validation data for hyperparameter tuning hinders practical deployment by incurring high…

Machine Learning · Computer Science 2026-02-27 Youngjoon Lee , Hyukjoon Lee , Seungrok Jung , Andy Luo , Jinu Gong , Yang Cao , Joonhyuk Kang

Large pre-trained models (LPMs) have demonstrated exceptional performance in diverse natural language processing and computer vision tasks. However, fully fine-tuning these models poses substantial memory challenges, particularly in…

Machine Learning · Computer Science 2024-09-12 Chengwei Sun , Jiwei Wei , Yujia Wu , Yiming Shi , Shiyuan He , Zeyu Ma , Ning Xie , Yang Yang

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Machine Learning · Computer Science 2023-08-01 Vithursan Thangarasa , Abhay Gupta , William Marshall , Tianda Li , Kevin Leong , Dennis DeCoste , Sean Lie , Shreyas Saxena

Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data, presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods…

Machine Learning · Computer Science 2024-12-10 Yongxian Wei , Zixuan Hu , Zhenyi Wang , Li Shen , Chun Yuan , Dacheng Tao

Gaussian processes (GPs) are crucial in machine learning for quantifying uncertainty in predictions. However, their associated covariance matrices, defined by kernel functions, are typically dense and large-scale, posing significant…

Machine Learning · Computer Science 2025-04-02 Theresa Wagner , Tianshi Xu , Franziska Nestler , Yuanzhe Xi , Martin Stoll

Meshfree simulation methods are emerging as compelling alternatives to conventional mesh-based approaches, particularly in the fields of Computational Fluid Dynamics (CFD) and continuum mechanics. In this publication, we provide a…

Machine Learning · Computer Science 2024-03-21 Paulami Banerjee , Mohan Padmanabha , Chaitanya Sanghavi , Isabel Michel , Simone Gramsch

We study the problem of Reinforcement Learning (RL) using as few real-world samples as possible. A naive application of RL can be inefficient in large and continuous state spaces. We present two versions of Multi-Fidelity Reinforcement…

Robotics · Computer Science 2020-03-10 Varun Suryan , Nahush Gondhalekar , Pratap Tokekar

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

Despite their exceptional performance on various tasks after fine-tuning, pre-trained language models (PLMs) face significant challenges due to growing privacy concerns with data in centralized training methods. We consider federated…

Machine Learning · Computer Science 2024-05-28 Yuxuan Yan , Qianqian Yang , Shunpu Tang , Zhiguo Shi

Maximum likelihood estimation of generalized linear mixed models(GLMMs) is difficult due to marginalization of the random effects. Computing derivatives of a fitted GLMM's likelihood (with respect to model parameters) is also difficult,…

Methodology · Statistics 2022-12-12 Ting Wang , Benjamin Graves , Yves Rosseel , Edgar C. Merkle

Stochastic proximal point methods have recently garnered renewed attention within the optimization community, primarily due to their desirable theoretical properties. Notably, these methods exhibit a convergence rate that is independent of…

Optimization and Control · Mathematics 2024-12-19 Elnur Gasanov , Peter Richtárik

Deep learning-based fault diagnosis (FD) approaches require a large amount of training data, which are difficult to obtain since they are located across different entities. Federated learning (FL) enables multiple clients to collaboratively…

Machine Learning · Computer Science 2023-10-16 Jixuan Cui , Jun Li , Zhen Mei , Kang Wei , Sha Wei , Ming Ding , Wen Chen , Song Guo

Low-rank adaptation (LoRA) and its variants have recently gained much interest due to their ability to avoid excessive inference costs. However, LoRA still encounters the following challenges: (1) Limitation of low-rank assumption; and (2)…

Computation and Language · Computer Science 2024-09-26 Qibin Wang , Xiaolin Hu , Weikai Xu , Wei Liu , Jian Luan , Bin Wang

Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical evidence that many LLM gradient matrices are effectively…

Machine Learning · Computer Science 2026-03-24 Zehao Li , Tao Ren , Zishi Zhang , Xi Chen , Yijie Peng