English
Related papers

Related papers: GRAIL: Post-hoc Compensation by Linear Reconstruct…

200 papers

Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several…

Machine Learning · Computer Science 2021-03-18 Lusine Abrahamyan , Yiming Chen , Giannis Bekoulis , Nikos Deligiannis

Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information. Learning a good inverse mapping from training…

Computer Vision and Pattern Recognition · Computer Science 2018-06-12 Morteza Mardani , Qingyun Sun , Shreyas Vasawanala , Vardan Papyan , Hatef Monajemi , John Pauly , David Donoho

A primary function of back-propagation is to compute both the gradient of hidden representations and parameters for optimization with gradient descent. Training large models requires high computational costs due to their vast parameter…

Machine Learning · Computer Science 2024-04-23 Enmao Diao , Qi Le , Suya Wu , Xinran Wang , Ali Anwar , Jie Ding , Vahid Tarokh

The unstructured sparsity after pruning poses a challenge to the efficient implementation of deep learning models in existing regular architectures like systolic arrays. On the other hand, coarse-grained structured pruning is suitable for…

Machine Learning · Computer Science 2024-11-22 Xizi Chen , Jingyang Zhu , Jingbo Jiang , Chi-Ying Tsui

Automated detection of grain boundaries (GBs) in electron microscope images of polycrystalline materials could help accelerate the nanoscale characterization of myriad engineering materials and novel materials under scientific research.…

Materials Science · Physics 2025-11-06 Doruk Aksoy , Huolin L. Xin , Timothy J. Rupert , William J. Bowman

Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, adapting LLMs to effectively handle structural data, such as knowledge graphs or web…

Computation and Language · Computer Science 2025-11-12 Jiarui Feng , Donghong Cai , Yixin Chen , Muhan Zhang

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

The introduction of the generative adversarial imitation learning (GAIL) algorithm has spurred the development of scalable imitation learning approaches using deep neural networks. Many of the algorithms that followed used a similar…

Machine Learning · Computer Science 2023-09-21 Kai Arulkumaran , Dan Ogawa Lillrank

In this paper we develop the Greedy Recombination Interpolation Method (GRIM) for finding sparse approximations of functions initially given as linear combinations of some (large) number of simpler functions. In a similar spirit to the…

Numerical Analysis · Mathematics 2024-03-11 Terry Lyons , Andrew D. McLeod

Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based…

Image and Video Processing · Electrical Eng. & Systems 2022-07-19 Batu Ozturkler , Arda Sahiner , Tolga Ergen , Arjun D Desai , Christopher M Sandino , Shreyas Vasanawala , John M Pauly , Morteza Mardani , Mert Pilanci

Prompt-based continual learning (CL) provides a parameter-efficient approach for adapting large language models (LLMs) across task sequences. However, most existing methods rely on task-aware inference and maintain a growing set of…

Machine Learning · Computer Science 2025-10-02 Anushka Tiwari , Sayantan Pal , Rohini K. Srihari , Kaiyi Ji

Computational reconstruction plays a vital role in computer vision and computational photography. Most of the conventional optimization and deep learning techniques explore local information for reconstruction. Recently, nonlocal low-rank…

Image and Video Processing · Electrical Eng. & Systems 2023-01-10 Daoyu Li , Hanwen Xu , Miao Cao , Xin Yuan , David J. Brady , Liheng Bian

Data-parallel distributed training of deep neural networks (DNN) has gained very widespread adoption, but can still experience communication bottlenecks. To address this issue, entire families of compression mechanisms have been developed,…

Machine Learning · Computer Science 2023-06-12 Mohammadreza Alimohammadi , Ilia Markov , Elias Frantar , Dan Alistarh

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Yu Qian , Jian Cao , Xiaoshuang Li , Jie Zhang , Hufei Li , Jue Chen

The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine-tuning. This practice is considered safe, as no current…

Machine Learning · Computer Science 2024-07-02 Eliahu Horwitz , Jonathan Kahana , Yedid Hoshen

Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Language-Image Pre-trained (CLIP) models have shown strong potential for CIL due to their…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Tianqi Wang , Jingcai Guo

Recovering sparse conditional independence graphs from data is a fundamental problem in machine learning with wide applications. A popular formulation of the problem is an $\ell_1$ regularized maximum likelihood estimation. Many convex…

Machine Learning · Computer Science 2019-12-24 Harsh Shrivastava , Xinshi Chen , Binghong Chen , Guanghui Lan , Srinvas Aluru , Han Liu , Le Song

Gradient descent can be surprisingly good at optimizing deep neural networks without overfitting and without explicit regularization. We find that the discrete steps of gradient descent implicitly regularize models by penalizing gradient…

Machine Learning · Computer Science 2022-07-20 David G. T. Barrett , Benoit Dherin

Purpose: To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning. Theory and Methods:…

Computer Vision and Pattern Recognition · Computer Science 2017-04-04 Kerstin Hammernik , Teresa Klatzer , Erich Kobler , Michael P Recht , Daniel K Sodickson , Thomas Pock , Florian Knoll

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Machine Learning · Computer Science 2018-02-21 Yusuke Tsuzuku , Hiroto Imachi , Takuya Akiba