English
Related papers

Related papers: Finding Manifolds With Bilinear Autoencoders

200 papers

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

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…

Machine Learning · Statistics 2019-04-15 Aditya Grover , Stefano Ermon

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Machine Learning · Computer Science 2024-09-10 Liv Gorton

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal components of PCA by…

Machine Learning · Computer Science 2026-01-28 Qipeng Zhan , Zhuoping Zhou , Zexuan Wang , Li Shen

The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In this work, we conduct a comprehensive analysis of how vision…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives…

Machine Learning · Computer Science 2025-07-01 Kenny Peng , Rajiv Movva , Jon Kleinberg , Emma Pierson , Nikhil Garg

While many phenomena in physics and engineering are formally high-dimensional, their long-time dynamics often live on a lower-dimensional manifold. The present work introduces an autoencoder framework that combines implicit regularization…

Machine Learning · Computer Science 2023-12-07 Kevin Zeng , Carlos E. Pérez De Jesús , Andrew J. Fox , Michael D. Graham

Autoencoders are commonly used in representation learning. They consist of an encoder and a decoder, which provide a straightforward way to map n-dimensional data in input space to a lower m-dimensional representation space and back. The…

Machine Learning · Computer Science 2021-11-16 Viktoria Schuster , Anders Krogh

Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to…

Computer Vision and Pattern Recognition · Computer Science 2019-12-30 Anupriya Gogna , Angshul Majumdar

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

Information Retrieval · Computer Science 2023-10-06 Eunseong Choi , Sunkyung Lee , Minjin Choi , Hyeseon Ko , Young-In Song , Jongwuk Lee

Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…

Principal components analysis (PCA) is the optimal linear auto-encoder of data, and it is often used to construct features. Enforcing sparsity on the principal components can promote better generalization, while improving the…

Machine Learning · Computer Science 2015-02-25 Malik Magdon-Ismail , Christos Boutsidis

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

This paper presents the geometric aspect of the autoencoder framework, which, despite its importance, has been relatively less recognized. Given a set of high-dimensional data points that approximately lie on some lower-dimensional…

Machine Learning · Computer Science 2023-09-28 Yonghyeon Lee

Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…

Machine Learning · Computer Science 2025-12-17 Albert Miao , Chenliang Zhou , Jiawei Zhou , Cengiz Oztireli

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most…

Machine Learning · Computer Science 2025-07-14 Gonçalo Paulo , Nora Belrose

Autoencoders are a powerful and versatile tool often used for various problems such as anomaly detection, image processing and machine translation. However, their reconstructions are not always trivial to explain. Therefore, we propose a…

Machine Learning · Computer Science 2023-03-22 Kenyu Kobayashi , Renata Khasanova , Arno Schneuwly , Felix Schmidt , Matteo Casserini

An important component of autoencoders is the method by which the information capacity of the latent representation is minimized or limited. In this work, the rank of the covariance matrix of the codes is implicitly minimized by relying on…

Machine Learning · Computer Science 2020-10-15 Li Jing , Jure Zbontar , Yann LeCun

Learning-based surrogate models have become a practical alternative to high-fidelity CFD solvers, but their latent representations remain opaque and hinder adoption in safety-critical or regulation-bound settings. This work introduces a…

Computational Engineering, Finance, and Science · Computer Science 2025-07-23 Yeping Hu , Shusen Liu
‹ Prev 1 4 5 6 7 8 10 Next ›