English
Related papers

Related papers: Interpretable non-linear dimensionality reduction …

200 papers

Understanding internal representations of neural models is a core interest of mechanistic interpretability. Due to its large dimensionality, the representation space can encode various aspects about inputs. To what extent are different…

Machine Learning · Computer Science 2026-05-15 Xinting Huang , Michael Hahn

Word embeddings are useful for a wide variety of tasks, but they lack interpretability. By rotating word spaces, interpretable dimensions can be identified while preserving the information contained in the embeddings without any loss. In…

Computation and Language · Computer Science 2019-09-16 Philipp Dufter , Hinrich Schütze

Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data across domains. Dimensionality-reduction algorithms involve complex optimizations and the reduced dimensions computed by these algorithms…

Human-Computer Interaction · Computer Science 2017-08-16 Marco Cavallo , Çağatay Demiralp

This paper shows that dimensionality reduction methods such as UMAP and t-SNE, can be approximately recast as MAP inference methods corresponding to a model introduced in Ravuri et al. (2023), that describes the graph Laplacian (an estimate…

Machine Learning · Statistics 2025-05-13 Aditya Ravuri , Neil D. Lawrence

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Nonlinear dimension reduction (NLDR) techniques such as tSNE, and UMAP provide a low-dimensional representation of high-dimensional data ($p\text{-}D$) by applying a nonlinear transformation. NLDR often exaggerates random patterns. But NLDR…

We develop a linear-algebraic framework for dimensional analysis in systems with constraints, particularly when variables are numerous or related by implicit relations so that direct elimination is impractical. By expressing both…

Mathematical Physics · Physics 2026-03-31 Umpei Miyamoto

Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Nikita Malik , Pratinav Seth , Neeraj Kumar Singh , Chintan Chitroda , Vinay Kumar Sankarapu

This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis. Such interpretable directions correspond to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 James Oldfield , Markos Georgopoulos , Yannis Panagakis , Mihalis A. Nicolaou , Ioannis Patras

Image decomposition aims to analyze an image into elementary components, which is essential for numerous downstream tasks and also by nature provides certain interpretability to the analysis. Deep learning can be powerful for such tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Sihan Wang , Shangqi Gao , Fuping Wu , Xiahai Zhuang

It is now known that an extended Gaussian process model equipped with rescaling can adapt to different smoothness levels of a function valued parameter in many nonparametric Bayesian analyses, offering a posterior convergence rate that is…

Statistics Theory · Mathematics 2011-12-06 Surya T. Tokdar

Analyzing high-dimensional data presents challenges due to the "curse of dimensionality'', making computations intensive. Dimension reduction techniques, categorized as linear or non-linear, simplify such data. Non-linear methods are…

Machine Learning · Statistics 2025-04-15 Praveen T. W. Hettige , Benjamin W. Ong

The importance of explainability in machine learning continues to grow, as both neural-network architectures and the data they model become increasingly complex. Unique challenges arise when a model's input features become high dimensional:…

Machine Learning · Computer Science 2021-12-21 Damien de Mijolla , Christopher Frye , Markus Kunesch , John Mansir , Ilya Feige

Visualizing high dimensional data by projecting them into two or three dimensional space is one of the most effective ways to intuitively understand the data's underlying characteristics, for example their class neighborhood structure.…

Machine Learning · Computer Science 2020-04-06 Pitoyo Hartono

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each…

Machine Learning · Computer Science 2025-11-18 Leo Gao , Achyuta Rajaram , Jacob Coxon , Soham V. Govande , Bowen Baker , Dan Mossing

Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Bangjie Yin , Luan Tran , Haoxiang Li , Xiaohui Shen , Xiaoming Liu

Sparse neural networks are often hypothesized to be more interpretable than dense models, motivated by findings that weight sparsity can produce compact circuits in language models. However, it remains unclear whether structural sparsity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Siyu Zhang

This thesis focuses on data that has complex spatio-temporal structure and on probabilistic graphical models that learn the structure in an interpretable and scalable manner. We target two research areas of interest: Gaussian graphical…

Machine Learning · Computer Science 2023-01-18 Yu Wang

The paper introduces a methodology for visualizing on a dimension reduced subspace the classification structure and the geometric characteristics induced by an estimated Gaussian mixture model for discriminant analysis. In particular, we…

Methodology · Statistics 2015-08-10 Luca Scrucca

We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that…

Computer Vision and Pattern Recognition · Computer Science 2016-08-02 Yannis Kalantidis , Clayton Mellina , Simon Osindero