English
Related papers

Related papers: Sparse $L^1$-Autoencoders for Scientific Data Comp…

200 papers

Autoencoders are powerful machine learning models used to compress information from multiple data sources. However, autoencoders, like all artificial neural networks, are often unidentifiable and uninterpretable. This research focuses on…

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Philipp Wesp , Robbie Holland , Vasiliki Sideri-Lampretsa , Sergios Gatidis

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing…

Machine Learning · Statistics 2017-07-14 Devansh Arpit , Yingbo Zhou , Hung Q. Ngo , Nils Napp , Venu Govindaraju

Scientific applications are generating unprecedented volumes of data that overwhelm storage and transmission systems, posing significant challenges for the design of data management tools and scientific databases. Lossy compression has…

Graphics · Computer Science 2026-04-09 Yuxiao Li , Mingze Xia , Xin Liang , Bei Wang , Hanqi Guo

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

Artificial Intelligence · Computer Science 2025-12-12 Nick Jiang , Xiaoqing Sun , Lisa Dunlap , Lewis Smith , Neel Nanda

In general, large datasets enable deep learning models to perform with good accuracy and generalizability. However, massive high-fidelity simulation datasets (from molecular chemistry, astrophysics, computational fluid dynamics (CFD), etc.…

Machine Learning · Computer Science 2022-07-27 Wai Tong Chung , Ki Sung Jung , Jacqueline H. Chen , Matthias Ihme

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

We explore an error-bounded lossy compression approach for reducing scientific data associated with 2D/3D unstructured meshes. While existing lossy compressors offer a high compression ratio with bounded error for regular grid data,…

Graphics · Computer Science 2024-04-04 Congrong Ren , Xin Liang , Hanqi Guo

Today's HPC applications are producing extremely large amounts of data, such that data storage and analysis are becoming more challenging for scientific research. In this work, we design a new error-controlled lossy compression algorithm…

Information Theory · Computer Science 2017-06-14 Dingwen Tao , Sheng Di , Zizhong Chen , Franck Cappello

The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a…

Machine Learning · Computer Science 2023-10-26 Alokendu Mazumder , Tirthajit Baruah , Bhartendu Kumar , Rishab Sharma , Vishwajeet Pattanaik , Punit Rathore

Data compression is becoming critical for storing scientific data because many scientific applications need to store large amounts of data and post process this data for scientific discovery. Unlike image and video compression algorithms…

Machine Learning · Computer Science 2022-12-22 Tania Banerjee , Jong Choi , Jaemoon Lee , Qian Gong , Jieyang Chen , Scott Klasky , Anand Rangarajan , Sanjay Ranka

Sparse support recovery arises in many applications in communications and signal processing. Existing methods tackle sparse support recovery problems for a given measurement matrix, and cannot flexibly exploit the properties of sparsity…

Information Theory · Computer Science 2019-10-11 Shuaichao Li , Wanqing Zhang , Ying Cui , Hei Victor Cheng , Wei Yu

Today's scientific simulations, for example in the high-performance exascale sector, produce huge amounts of data. Due to limited I/O bandwidth and available storage space, there is the necessity to reduce scientific data of high…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-25 N. Böing , J. Holke , C. Hergl , L. Spataro , G. Gassner , A. Basermann

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…

Machine Learning · Computer Science 2026-05-28 Tue M. Cao , Nguyen Do , My T. Thai

We propose a strategy to compress and store large volumes of scientific data represented on unstructured grids. Approaches utilizing tensor decompositions for data compression have already been proposed. Here, data on a structured grid is…

Numerical Analysis · Mathematics 2024-09-23 Prashant Rai , Hemanth Kolla , Lewis Cannada , Alex Gorodetsky

Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of…

Neural and Evolutionary Computing · Computer Science 2022-12-05 Richard J. Preen , Stewart W. Wilson , Larry Bull

Autoencoders receive latent models of input data. It was shown in recent works that they also estimate probability density functions of the input. This fact makes using the Bayesian decision theory possible. If we obtain latent models of…

Computer Vision and Pattern Recognition · Computer Science 2018-11-07 Vasily Morzhakov

Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…

Data Analysis, Statistics and Probability · Physics 2025-08-18 Alexander Yue , Haoyi Jia , Julia Gonski