English
Related papers

Related papers: Improved Training of Sparse Coding Variational Aut…

200 papers

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimensional concept space into a…

Machine Learning · Computer Science 2026-03-31 Vitória Barin Pacela , Shruti Joshi , Isabela Camacho , Simon Lacoste-Julien , David Klindt

Current state-of-the-art generative approaches frequently rely on a two-stage training procedure, where an autoencoder (often a VAE) first performs dimensionality reduction, followed by training a generative model on the learned latent…

Machine Learning · Statistics 2025-07-15 Gianluigi Silvestri , Luca Ambrogioni

Sparse coding is an unsupervised learning algorithm that learns a succinct high-level representation of the inputs given only unlabeled data; it represents each input as a sparse linear combination of a set of basis functions. Originally…

Machine Learning · Computer Science 2012-06-26 Roger Grosse , Rajat Raina , Helen Kwong , Andrew Y. Ng

As deep Variational Auto-Encoder (VAE) frameworks become more widely used for modeling biomolecular simulation data, we emphasize the capability of the VAE architecture to concurrently maximize the timescale of the latent space while…

Chemical Physics · Physics 2021-12-08 Hannah K. Wayment-Steele , Vijay S. Pande

Variational Autoencoders (VAEs) have played a key role in scaling up diffusion-based generative models, as in Stable Diffusion, yet questions regarding their robustness remain largely underexplored. Although adversarial training has been an…

Machine Learning · Computer Science 2025-04-25 Hyomin Lee , Minseon Kim , Sangwon Jang , Jongheon Jeong , Sung Ju Hwang

A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…

Computer Vision and Pattern Recognition · Computer Science 2017-12-12 Dimitrios C. Gklezakos , Rajesh P. N. Rao

Traditional supervised denoisers are trained using pairs of noisy input and clean target images. They learn to predict a central tendency of the posterior distribution over possible clean images. When, e.g., trained with the popular…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Benjamin Salmon , Alexander Krull

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Qinyu Zhao , Guangting Zheng , Tao Yang , Rui Zhu , Xingjian Leng , Stephen Gould , Liang Zheng

We propose a theoretical approach towards the training numerical stability of Variational AutoEncoders (VAE). Our work is motivated by recent studies empowering VAEs to reach state of the art generative results on complex image datasets.…

Machine Learning · Computer Science 2021-06-28 David Dehaene , Rémy Brossard

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model's sensitivity to its…

Machine Learning · Computer Science 2024-12-31 Gabriela Sejnova , Michal Vavrecka , Karla Stepanova

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also…

Machine Learning · Computer Science 2019-11-15 Felix Berkhahn , Richard Keys , Wajih Ouertani , Nikhil Shetty , Dominik Geißler

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders and generative adversarial networks, is now a key technique…

Computer Vision and Pattern Recognition · Computer Science 2019-10-08 Wenju Xu , Shawn Keshmiri , Guanghui Wang

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

Selective manipulation of data attributes using deep generative models is an active area of research. In this paper, we present a novel method to structure the latent space of a Variational Auto-Encoder (VAE) to encode different…

Machine Learning · Computer Science 2020-07-30 Ashis Pati , Alexander Lerch

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

Machine Learning · Computer Science 2025-02-06 Abhinav Menon , Manish Shrivastava , David Krueger , Ekdeep Singh Lubana

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Machine Learning · Computer Science 2025-08-14 Charles O'Neill , Mudith Jayasekara , Max Kirkby

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…

Machine Learning · Computer Science 2017-03-07 Xi Chen , Diederik P. Kingma , Tim Salimans , Yan Duan , Prafulla Dhariwal , John Schulman , Ilya Sutskever , Pieter Abbeel

Hybrid recommendations have recently attracted a lot of attention where user features are utilized as auxiliary information to address the sparsity problem caused by insufficient user-item interactions. However, extracted user features…

Information Retrieval · Computer Science 2022-11-22 Yaochen Zhu , Zhenzhong Chen
‹ Prev 1 3 4 5 6 7 10 Next ›