English
Related papers

Related papers: LocoProp: Enhancing BackProp via Local Loss Optimi…

200 papers

Second-order optimization methods are computationally expensive for large-scale problems. Recently, Doikov, Chayti, and Jaggi (ICML 2023) proposed the LazyCRN method that reduces computation by studying the gradient complexity of…

Optimization and Control · Mathematics 2026-01-26 Lesi Chen , Chengchang Liu , Luo Luo , Jingzhao Zhang

Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains. In this work, we introduce a new retrospective loss to improve the training of deep neural network models by utilizing the prior…

Computer Vision and Pattern Recognition · Computer Science 2020-06-25 Surgan Jandial , Ayush Chopra , Mausoom Sarkar , Piyush Gupta , Balaji Krishnamurthy , Vineeth Balasubramanian

Fast gradient-based optimization algorithms have become increasingly essential for the computationally efficient training of machine learning models. One technique is to multiply the gradient by a preconditioner matrix to produce a step,…

Machine Learning · Computer Science 2023-09-12 Isaac Liao , Rumen R. Dangovski , Jakob N. Foerster , Marin Soljačić

With the increasing popularity of deep learning in image processing, many learned lossless image compression methods have been proposed recently. One group of algorithms that have shown good performance are based on learned pixel-based…

Image and Video Processing · Electrical Eng. & Systems 2022-12-27 Fatih Kamisli

Handling the ever-increasing scale of contemporary deep learning and transformer-based models poses a significant challenge. Overparameterized Transformer networks outperform prior art in Natural Language processing and Computer Vision.…

Machine Learning · Computer Science 2024-11-05 Soheil Zibakhsh Shabgahi , Mohammad Sohail Shariff , Farinaz Koushanfar

Locally supervised learning aims to train a neural network based on a local estimation of the global loss function at each decoupled module of the network. Auxiliary networks are typically appended to the modules to approximate the gradient…

Machine Learning · Computer Science 2022-08-02 Hasnain Irshad Bhatti , Jaekyun Moon

Motivated by big data applications, first-order methods have been extremely popular in recent years. However, naive gradient methods generally converge slowly. Hence, much efforts have been made to accelerate various first-order methods.…

Optimization and Control · Mathematics 2016-06-30 Yangyang Xu

There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High…

Machine Learning · Computer Science 2019-06-12 Stanislav Fort , Stanislaw Jastrzebski

Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…

Machine Learning · Computer Science 2023-12-13 Arnav Chavan , Nahush Lele , Deepak Gupta

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a…

Machine Learning · Computer Science 2020-04-29 Ted Moskovitz , Rui Wang , Janice Lan , Sanyam Kapoor , Thomas Miconi , Jason Yosinski , Aditya Rawal

Fine-tuning large language models (LLMs) has achieved remarkable success across various NLP tasks, but the substantial memory overhead during backpropagation remains a critical bottleneck, especially as model scales grow. Zeroth-order (ZO)…

Computation and Language · Computer Science 2026-01-09 Feihu Jin , Shipeng Cen , Ying Tan

Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity. However, due to high number of new…

Machine Learning · Computer Science 2025-05-27 Habib Hajimolahoseini , Walid Ahmed , Yang Liu

Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely on heuristically hand-crafted metrics, potentially leading…

Machine Learning · Computer Science 2025-07-04 Yuan Gao , Zujing Liu , Weizhong Zhang , Bo Du , Gui-Song Xia

Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing one-shot pruning methods rely on local layer importance or…

Machine Learning · Computer Science 2026-05-28 Vincent-Daniel Yun , Youngrae Kim , Woosang Lim , YoungJin Heo , Minkyu Kim , Sunwoo Lee

A common practice in most of deep convolutional neural architectures is to employ fully-connected layers followed by Softmax activation to minimize cross-entropy loss for the sake of classification. Recent studies show that substitution or…

Machine Learning · Computer Science 2017-10-23 Arash Shahriari

Models with dominant advection always posed a difficult challenge for projection-based reduced order modelling. Many methodologies that have recently been proposed are based on the pre-processing of the full-order solutions to accelerate…

Numerical Analysis · Mathematics 2022-03-02 Davide Papapicco , Nicola Demo , Michele Girfoglio , Giovanni Stabile , Gianluigi Rozza

A quadratic approximation of neural network loss landscapes has been extensively used to study the optimization process of these networks. Though, it usually holds in a very small neighborhood of the minimum, it cannot explain many…

Machine Learning · Computer Science 2022-06-23 Chao Ma , Daniel Kunin , Lei Wu , Lexing Ying

Reduced order models are computationally inexpensive approximations that capture the important dynamical characteristics of large, high-fidelity computer models of physical systems. This paper applies machine learning techniques to improve…

Machine Learning · Computer Science 2015-11-11 Azam Moosavi , Razvan Stefanescu , Adrian Sandu

This paper presents a nonlinear model reduction method for systems of equations using a structured neural network. The neural network takes the form of a "three-layer" network with the first layer constrained to lie on the Grassmann…

Machine Learning · Computer Science 2020-12-21 Kayla Bollinger , Hayden Schaeffer

This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer's parameters change and whether the layer will continue…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Giorgio Cruciata , Luca Cruciata , Liliana Lo Presti , Jan Van Gemert , Marco La Cascia
‹ Prev 1 4 5 6 7 8 10 Next ›