English
Related papers

Related papers: Sparse and Faithful Explanations Without Sparse Mo…

200 papers

Debiased machine learning is a meta algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i.e. scalar summaries, of machine learning algorithms. For example, an analyst may desire the…

Machine Learning · Statistics 2022-10-25 Victor Chernozhukov , Whitney K. Newey , Rahul Singh

Kernel-based methods for support vector machines (SVM) have shown highly advantageous performance in various applications. However, they may incur prohibitive computational costs for large-scale sample datasets. Therefore, data reduction…

Optimization and Control · Mathematics 2021-04-27 Shenglong Zhou

Understanding the decisions made by deep neural networks is essential in high-stakes domains such as medical imaging and autonomous driving. Yet, these models often lack transparency, particularly in computer vision.…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Viktar Dubovik , Łukasz Struski , Jacek Tabor , Dawid Rymarczyk

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

Explainable Artificial Intelligence (XAI) methods (SHAP, LIME) are increasingly adopted to interpret models in high-stakes businesses. However, the credibility of these explanations, their stability under realistic data perturbations,…

Artificial Intelligence · Computer Science 2026-03-06 Alin-Gabriel Vaduva , Simona-Vasilica Oprea , Adela Bara

Consider a regression model with fixed design and Gaussian noise where the regression function can potentially be well approximated by a function that admits a sparse representation in a given dictionary. This paper resorts to exponential…

Statistics Theory · Mathematics 2013-01-08 Philippe Rigollet , Alexandre B. Tsybakov

We study the problem of variable selection in convex nonparametric regression. Under the assumption that the true regression function is convex and sparse, we develop a screening procedure to select a subset of variables that contains the…

Statistics Theory · Mathematics 2014-11-19 Min Xu , Minhua Chen , John Lafferty

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

Sparse regression and classification estimators that respect group structures have application to an assortment of statistical and machine learning problems, from multitask learning to sparse additive modeling to hierarchical selection.…

Methodology · Statistics 2024-03-11 Ryan Thompson , Farshid Vahid

Sparse autoencoders (SAEs) are a promising approach for uncovering interpretable features in large language models (LLMs). While several automated evaluation methods exist for SAEs, most rely on external LLMs. In this work, we introduce…

Computation and Language · Computer Science 2025-09-30 Alex Gulko , Yusen Peng , Sachin Kumar

Disentanglement via mechanism sparsity was introduced recently as a principled approach to extract latent factors without supervision when the causal graph relating them in time is sparse, and/or when actions are observed and affect them…

Machine Learning · Statistics 2022-07-19 Sébastien Lachapelle , Simon Lacoste-Julien

Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be…

Machine Learning · Computer Science 2020-01-17 Michael Hind , Dennis Wei , Yunfeng Zhang

Sparse methods are the standard approach to obtain interpretable models with high prediction accuracy. Alternatively, algorithmic ensemble methods can achieve higher prediction accuracy at the cost of loss of interpretability. However, the…

Methodology · Statistics 2022-01-11 Anthony Christidis , Stefan Van Aelst , Ruben Zamar

Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Gerasimos Chatzoudis , Zhuowei Li , Gemma E. Moran , Hao Wang , Dimitris N. Metaxas

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Machine Learning · Computer Science 2026-05-19 George Ma , Zhongyuan Liang , Irene Y. Chen , Somayeh Sojoudi

Latent variable models are powerful statistical tools that can uncover relevant variation between patients or cells, by inferring unobserved hidden states from observable high-dimensional data. A major shortcoming of current methods,…

Machine Learning · Statistics 2022-04-12 Arber Qoku , Florian Buettner

A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical…

Machine Learning · Computer Science 2015-08-25 Rémi Gribonval , Rodolphe Jenatton , Francis Bach

When applying the support vector machine (SVM) to high-dimensional classification problems, we often impose a sparse structure in the SVM to eliminate the influences of the irrelevant predictors. The lasso and other variable selection…

Machine Learning · Statistics 2008-02-22 Seongho Wu , Hui Zou , Ming Yuan

Standard selective prediction methods typically estimate uncertainty from the output of a single predictive branch. While effective for general uncertainty estimation, these approaches often struggle under partial observability, where local…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Kartik Jhawar , Yuhao Geng , Atul N. Parikh , Lipo Wang

Semi-supervised learning plays an important role in large-scale machine learning. Properly using additional unlabeled data (largely available nowadays) often can improve the machine learning accuracy. However, if the machine learning model…

Machine Learning · Computer Science 2017-05-02 Zhaocai Sun , William K. Cheung , Xiaofeng Zhang , Jun Yang
‹ Prev 1 4 5 6 7 8 10 Next ›