English
Related papers

Related papers: Sinkhorn AutoEncoders

200 papers

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture non-semantic…

Computation and Language · Computer Science 2025-10-03 Jiaqing Xie

We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure…

Information Retrieval · Computer Science 2019-12-10 Feng Nan , Ran Ding , Ramesh Nallapati , Bing Xiang

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

Machine Learning · Computer Science 2025-05-20 Jeremy Budd , Javier Ideami , Benjamin Macdowall Rynne , Keith Duggar , Randall Balestriero

We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders. We highlight the…

Machine Learning · Statistics 2018-02-13 Paul K. Rubenstein , Bernhard Schoelkopf , Ilya Tolstikhin

Principal Component Analysis (PCA) minimizes the reconstruction error given a class of linear models of fixed component dimensionality. Probabilistic PCA adds a probabilistic structure by learning the probability distribution of the PCA…

Machine Learning · Computer Science 2022-09-20 Vanessa Böhm , Uroš Seljak

Trajectory generation and prediction are two interwoven tasks that play important roles in planner evaluation and decision making for intelligent vehicles. Most existing methods focus on one of the two and are optimized to directly output…

Robotics · Computer Science 2022-11-02 Ruochen Jiao , Xiangguo Liu , Bowen Zheng , Dave Liang , Qi Zhu

The ability to compare two degenerate probability distributions (i.e. two probability distributions supported on two distinct low-dimensional manifolds living in a much higher-dimensional space) is a crucial problem arising in the…

Machine Learning · Statistics 2017-10-23 Aude Genevay , Gabriel Peyré , Marco Cuturi

Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the seminal Vector Quantized Variational Auto-Encoder (VQ-VAE),…

Machine Learning · Computer Science 2023-06-21 Tung-Long Vuong , Trung Le , He Zhao , Chuanxia Zheng , Mehrtash Harandi , Jianfei Cai , Dinh Phung

The process of tuning the size of the hidden layers for autoencoders has the benefit of providing optimally compressed representations for the input data. However, such hyper-parameter tuning process would take a lot of computation and time…

Machine Learning · Computer Science 2025-07-08 Sarthak Ketanbhai Modi , Zi Pong Lim , Yushi Cao , Yupeng Cheng , Yon Shin Teo , Shang-Wei Lin

In state estimation tasks, the usual assumption of exactly known disturbance distribution is often unrealistic and renders the estimator fragile in practice. The recently emerging Wasserstein distributionally robust state estimation (DRSE)…

Optimization and Control · Mathematics 2026-02-10 Yulin Feng , Xianyu Li , Steven X. Ding , Hao Ye , Chao Shang

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Machine Learning · Computer Science 2025-12-08 Antonio Bărbălau , Cristian Daniel Păduraru , Teodor Poncu , Alexandru Tifrea , Elena Burceanu

In this work, we propose a sparse transformer architecture that incorporates prior information about the underlying data distribution directly into the transformer structure of the neural network. The design of the model is motivated by a…

Machine Learning · Computer Science 2025-10-21 Fuqun Han , Stanley Osher , Wuchen Li

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

Machine Learning · Statistics 2019-06-04 Giulia Luise , Alessandro Rudi , Massimiliano Pontil , Carlo Ciliberto

One of the key challenges in learning joint embeddings of multiple modalities, e.g. of images and text, is to ensure coherent cross-modal semantics that generalize across datasets. We propose to address this through joint Gaussian…

Computer Vision and Pattern Recognition · Computer Science 2019-09-17 Shweta Mahajan , Teresa Botschen , Iryna Gurevych , Stefan Roth

Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provide an accurate representation of…

Machine Learning · Statistics 2023-01-18 Liyun Tu , Austin Talbot , Neil Gallagher , David Carlson

Maximizing the user-item engagement based on vectorized embeddings is a standard procedure of recent recommender models. Despite the superior performance for item recommendations, these methods however implicitly deprioritize the modeling…

Information Retrieval · Computer Science 2023-05-09 Yankai Chen , Yifei Zhang , Menglin Yang , Zixing Song , Chen Ma , Irwin King

We introduce COT-GAN, an adversarial algorithm to train implicit generative models optimized for producing sequential data. The loss function of this algorithm is formulated using ideas from Causal Optimal Transport (COT), which combines…

Machine Learning · Statistics 2020-10-23 Tianlin Xu , Li K. Wenliang , Michael Munn , Beatrice Acciaio

Variational Auto-Encoder (VAE) has been widely applied as a fundamental generative model in machine learning. For complex samples like imagery objects or scenes, however, VAE suffers from the dimensional dilemma between reconstruction…

Machine Learning · Computer Science 2020-02-18 Deli Zhao , Jiapeng Zhu , Bo Zhang

In this paper, we study the problem of learning compact (low-dimensional) representations for sequential data that captures its implicit spatio-temporal cues. To maximize extraction of such informative cues from the data, we set the problem…

Machine Learning · Computer Science 2020-07-14 Anoop Cherian , Shuchin Aeron

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Machine Learning · Computer Science 2026-04-07 Matthew Levinson
‹ Prev 1 3 4 5 6 7 10 Next ›