Adbench: Anomaly detection benchmark

S Han, X Hu, H Huang, M Jiang… - Advances in Neural …, 2022 - proceedings.neurips.cc
Given a long list of anomaly detection algorithms developed in the last few decades, how do
they perform with regard to (i) varying levels of supervision,(ii) different types of anomalies …

Learning to optimize: A primer and a benchmark

T Chen, X Chen, W Chen, H Heaton, J Liu… - Journal of Machine …, 2022 - jmlr.org
Learning to optimize (L2O) is an emerging approach that leverages machine learning to
develop optimization methods, aiming at reducing the laborious iterations of hand …

Lq-lora: Low-rank plus quantized matrix decomposition for efficient language model finetuning

H Guo, P Greengard, EP Xing, Y Kim - arXiv preprint arXiv:2311.12023, 2023 - arxiv.org
We propose a simple approach for memory-efficient adaptation of pretrained language
models. Our approach uses an iterative algorithm to decompose each pretrained matrix into …

Learning to optimize: A tutorial for continuous and mixed-integer optimization

X Chen, J Liu, W Yin - Science China Mathematics, 2024 - Springer
Learning to optimize (L2O) stands at the intersection of traditional optimization and machine
learning, utilizing the capabilities of machine learning to enhance conventional optimization …

Preconditioning matters: Fast global convergence of non-convex matrix factorization via scaled gradient descent

X Jia, H Wang, J Peng, X Feng… - Advances in Neural …, 2024 - proceedings.neurips.cc
Low-rank matrix factorization (LRMF) is a canonical problem in non-convex optimization, the
objective function to be minimized is non-convex and even non-smooth, which makes the …

Hyperparameter tuning is all you need for LISTA

X Chen, J Liu, Z Wang, W Yin - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract Learned Iterative Shrinkage-Thresholding Algorithm (LISTA) introduces the concept
of unrolling an iterative algorithm and training it like a neural network. It has had great …

Unified Framework for Faster Clustering via Joint Schatten -Norm Factorization With Optimal Mean

H Zhang, J Zhao, B Zhang, C Gong… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
To enhance the effectiveness and efficiency of subspace clustering in visual tasks, this work
introduces a novel approach that automatically eliminates the optimal mean, which is …

Optimization-inspired Cumulative Transmission Network for image compressive sensing

T Zhang, L Li, Z Peng - Knowledge-Based Systems, 2023 - Elsevier
Compressive Sensing (CS) techniques enable accurate signal reconstruction with few
measurements. Deep Unfolding Networks (DUNs) have recently been shown to increase the …

A Comprehensive Review of Trends, Applications and Challenges In Out-of-Distribution Detection

N Ghassemi, E Fazl-Ersi - arXiv preprint arXiv:2209.12935, 2022 - arxiv.org
With recent advancements in artificial intelligence, its applications can be seen in every
aspect of humans' daily life. From voice assistants to mobile healthcare and autonomous …

LR-CSNet: low-rank deep unfolding network for image compressive sensing

T Zhang, L Li, C Igel, S Oehmcke… - 2022 IEEE 8th …, 2022 - ieeexplore.ieee.org
Deep unfolding networks (DUNs) have proven to be a viable approach to compressive
sensing (CS). In this work, we propose a DUN called low-rank CS network (LR-CSNet) for …