Image de couverture de livre

Sparse and Faithful Explanations Without Sparse Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Yiyang, Chen, Zhi, Orlandi, Vittorio, Wang, Tong, Rudin, Cynthia
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Decision Sparsity
par: Sun, Yiyang, et autres
Publié: (2024)

Optimal Sparse Survival Trees
par: Zhang, Rui, et autres
Publié: (2024)

OKRidge: Scalable Optimal k-Sparse Ridge Regression
par: Liu, Jiachang, et autres
Publié: (2023)

Dimension Reduction with Locally Adjusted Graphs
par: Wang, Yingfan, et autres
Publié: (2024)

TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
par: Oublal, Khalid, et autres
Publié: (2026)

A Double Machine Learning Approach to Combining Experimental and Observational Data
par: Parikh, Harsh, et autres
Publié: (2023)

The Rashomon Effect for Visualizing High-Dimensional Data
par: Sun, Yiyang, et autres
Publié: (2026)

Sparse learned kernels for interpretable and efficient medical time series processing
par: Chen, Sully F., et autres
Publié: (2023)

Models That Are Interpretable But Not Transparent
par: Zhong, Chudi, et autres
Publié: (2025)

Leo Breiman, the Rashomon Effect, and the Occam Dilemma
par: Rudin, Cynthia
Publié: (2025)

Beyond Activation Patterns: A Weight-Based Out-of-Context Explanation of Sparse Autoencoder Features
par: Liu, Yiting, et autres
Publié: (2026)

FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
par: Liu, Jiachang, et autres
Publié: (2024)

FaithLM: Towards Faithful Explanations for Large Language Models
par: Chuang, Yu-Neng, et autres
Publié: (2024)

Navigating the Effect of Parametrization for Dimensionality Reduction
par: Huang, Haiyang, et autres
Publié: (2024)

Resolving Predictive Multiplicity for the Rashomon Set
par: Haghighat, Parian, et autres
Publié: (2026)

SparseDM: Toward Sparse Efficient Diffusion Models
par: Wang, Kafeng, et autres
Publié: (2024)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
par: Cho, Seonglae, et autres
Publié: (2025)

DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
par: Guo, Yuhan, et autres
Publié: (2025)

Interpretable Generalized Additive Models for Datasets with Missing Values
par: McTavish, Hayden, et autres
Publié: (2024)

Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks
par: Zhao, Jialin, et autres
Publié: (2024)

"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts
par: Babbar, Varun, et autres
Publié: (2024)

"Faithful to What?" On the Limits of Fidelity-Based Explanations
par: Eshbaugh, Jackson
Publié: (2025)

Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
par: Sarmiento, Paulo Yanez, et autres
Publié: (2024)

From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction
par: Tong, Yanjie, et autres
Publié: (2026)

Sparse Autoencoders, Again?
par: Lu, Yin, et autres
Publié: (2025)

DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
par: Wu, Yinjun, et autres
Publié: (2024)

The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance
par: Donnelly, Jon, et autres
Publié: (2023)

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
par: Engel, Andrew, et autres
Publié: (2023)

Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon Effect
par: Donnelly, Jon, et autres
Publié: (2025)

Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations
par: You, Lei, et autres
Publié: (2024)

Pruning for Sparse Diffusion Models based on Gradient Flow
par: Wan, Ben, et autres
Publié: (2025)

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
par: Yue, Linan, et autres
Publié: (2024)

SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization
par: Zhang, Taolin, et autres
Publié: (2026)

Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation
par: Zhong, Xuyang, et autres
Publié: (2024)

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated
par: Wang, Hongyu, et autres
Publié: (2024)

TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables
par: Soegeng, Hans Farrell, et autres
Publié: (2026)

Sparse-to-Sparse Training of Diffusion Models
par: Oliveira, Inês Cardoso, et autres
Publié: (2025)

PolytopeWalk: Sparse MCMC Sampling over Polytopes
par: Sun, Benny, et autres
Publié: (2024)

B-cos GNNs: Faithful Explanations through Dynamic Linearity
par: Groß, Joschka, et autres
Publié: (2026)

Low-Rank Adapting Models for Sparse Autoencoders
par: Chen, Matthew, et autres
Publié: (2025)