English
Related papers

Related papers: HOT: Hadamard-based Optimized Training

200 papers

With the rapid increase in model size and the growing importance of various fine-tuning applications, lightweight training has become crucial. Since the backward pass is twice as expensive as the forward pass, optimizing backpropagation is…

Computer Vision and Pattern Recognition · Computer Science 2024-06-24 Seonggon Kim , Eunhyeok Park

Collaborative filtering (CF) has been proven to be one of the most effective techniques for recommendation. Among all CF approaches, SimpleX is the state-of-the-art method that adopts a novel loss function and a proper number of negative…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-04 Chengming Zhang , Shaden Smith , Baixi Sun , Jiannan Tian , Jonathan Soifer , Xiaodong Yu , Shuaiwen Leon Song , Yuxiong He , Dingwen Tao

This paper proposes an efficient HOT algorithm for solving the optimal transport (OT) problems with finite supports. We particularly focus on an efficient implementation of the HOT algorithm for the case where the supports are in…

Optimization and Control · Mathematics 2025-04-17 Guojun Zhang , Zhexuan Gu , Yancheng Yuan , Defeng Sun

Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning…

Machine Learning · Computer Science 2025-11-06 Saleh Ashkboos , Mahdi Nikdan , Soroush Tabesh , Roberto L. Castro , Torsten Hoefler , Dan Alistarh

We propose Hierarchical Optimization Time Integration (HOT) for efficient implicit time-stepping of the Material Point Method (MPM) irrespective of simulated materials and conditions. HOT is an MPM-specialized hierarchical optimization…

Graphics · Computer Science 2020-04-28 Xinlei Wang , Minchen Li , Yu Fang , Xinxin Zhang , Ming Gao , Min Tang , Danny M. Kaufman , Chenfanfu Jiang

Hadamard transforms have become a key tool for stabilizing low-precision training, but existing methods apply them uniformly across tensors and computation paths. We show that this one-size-fits-all strategy is inherently limited: Hadamard…

Machine Learning · Computer Science 2026-05-11 Seonggon Kim , Alireza Khodamoradi , Pranathi Vasireddy , Kristof Denolf , Eunhyeok Park

Continual learning is a desirable feature in many modern machine learning applications, which allows in-field adaptation and updating, ranging from accommodating distribution shift, to fine-tuning, and to learning new tasks. For…

Machine Learning · Computer Science 2023-10-06 Martin Schiemer , Clemens JS Schaefer , Jayden Parker Vap , Mark James Horeni , Yu Emma Wang , Juan Ye , Siddharth Joshi

Reducing energy consumption has become a pressing need for modern machine learning, which has achieved many of its most impressive results by scaling to larger and more energy-consumptive neural networks. Unfortunately, the main algorithm…

Machine Learning · Computer Science 2025-07-10 Risi Jaiswal , Supriyo Datta , Joseph G. Makin

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…

Robotics · Computer Science 2023-02-22 Siddhant Haldar , Vaibhav Mathur , Denis Yarats , Lerrel Pinto

Current deep learning architectures are growing larger in order to learn from complex datasets. These architectures require giant matrix multiplication operations to train millions of parameters. Conversely, there is another growing trend…

Machine Learning · Statistics 2016-12-06 Ryan Spring , Anshumali Shrivastava

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

The Hadamard decomposition is a powerful technique for data analysis and matrix compression, which decomposes a given matrix into the element-wise product of two or more low-rank matrices. In this paper, we develop an efficient algorithm to…

Machine Learning · Computer Science 2025-04-23 Samuel Wertz , Arnaud Vandaele , Nicolas Gillis

The past decade has witnessed a surge of endeavors in statistical inference for high-dimensional sparse regression, particularly via de-biasing or relaxed orthogonalization. Nevertheless, these techniques typically require a more stringent…

Statistics Theory · Mathematics 2021-11-29 Yang Li , Zemin Zheng , Jia Zhou , Ziwei Zhu

Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this…

Machine Learning · Computer Science 2023-06-26 Haocheng Xi , Changhao Li , Jianfei Chen , Jun Zhu

Neural network accelerator is a key enabler for the on-device AI inference, for which energy efficiency is an important metric. The data-path energy, including the computation energy and the data movement energy among the arithmetic units,…

Computer Vision and Pattern Recognition · Computer Science 2020-02-14 Meng Li , Yilei Li , Pierce Chuang , Liangzhen Lai , Vikas Chandra

Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…

Machine Learning · Computer Science 2019-10-30 Ayan Chakrabarti , Benjamin Moseley

Deep Neural Networks are successful but highly computationally expensive learning systems. One of the main sources of time and energy drains is the well known backpropagation (backprop) algorithm, which roughly accounts for 2/3 of the…

Machine Learning · Computer Science 2020-04-17 Simon Wiedemann , Temesgen Mehari , Kevin Kepp , Wojciech Samek

Fine-tuning pre-trained language models for downstream tasks has achieved impressive results in NLP. However, fine-tuning all parameters becomes impractical due to the rapidly increasing size of model parameters. To address this, Parameter…

Computation and Language · Computer Science 2024-09-23 Geyuan Zhang , Xiaofei Zhou , Chuheng Chen

Future spacecraft and surface robotic missions require increasingly capable autonomy stacks for exploring challenging and unstructured domains, and trajectory optimization will be a cornerstone of such autonomy stacks. However, the…

Robotics · Computer Science 2024-09-18 Julia Briden , Changrak Choi , Kyongsik Yun , Richard Linares , Abhishek Cauligi

Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme low-bit quantization remains highly sensitive to activation outliers and anisotropic weight curvature. Existing…

Machine Learning · Computer Science 2026-05-29 Artur Zagitov , Gleb Molodtsov , Aleksandr Beznosikov
‹ Prev 1 2 3 10 Next ›