Imagen de Portada

Optimal ablation for interpretability

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Maximilian, Janson, Lucas
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: Generalized Baselines
por: Schiffer, Benjamin, et al.
Publicado: (2024)

Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: $\sqrt{T}$-Regret
por: Schiffer, Benjamin, et al.
Publicado: (2025)

The Relative Instability of Model Comparison with Cross-validation
por: Bayle, Alexandre, et al.
Publicado: (2025)

Chiseling: Powerful and Valid Subgroup Selection via Interactive Machine Learning
por: Cheng, Nathan, et al.
Publicado: (2025)

Bernstein-von Mises for Adaptively Collected Data
por: Du, Kevin, et al.
Publicado: (2025)

Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis
por: Ham, Dae Woong, et al.
Publicado: (2022)

Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits
por: Liang, Biyonka, et al.
Publicado: (2024)

Stabilizing Native Low-Rank LLM Pretraining
por: Janson, Paul, et al.
Publicado: (2026)

Forest-ORE: Mining Optimal Rule Ensemble to interpret Random Forest models
por: Maissae, Haddouchi, et al.
Publicado: (2024)

Learning Optimal Search Strategies
por: Ankirchner, Stefan, et al.
Publicado: (2026)

A New Perspective on Shampoo's Preconditioner
por: Morwani, Depen, et al.
Publicado: (2024)

Evaluating the Effectiveness of Index-Based Treatment Allocation
por: Boehmer, Niclas, et al.
Publicado: (2024)

A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning
por: Feigin, Shlomo Libo, et al.
Publicado: (2024)

Fishnets: Information-Optimal, Scalable Aggregation for Sets and Graphs
por: Makinen, T. Lucas, et al.
Publicado: (2023)

Heterogeneous Low-Bandwidth Pre-Training of LLMs
por: Obeidi, Yazan, et al.
Publicado: (2026)

Challenges in interpretability of additive models
por: Zhang, Xinyu, et al.
Publicado: (2025)

Are machine learning interpretations reliable? A stability study on global interpretations
por: Gan, Luqin, et al.
Publicado: (2025)

SOAP: Improving and Stabilizing Shampoo using Adam
por: Vyas, Nikhil, et al.
Publicado: (2024)

How to use and interpret activation patching
por: Heimersheim, Stefan, et al.
Publicado: (2024)

Bilinear autoencoders find interpretable manifolds
por: Dooms, Thomas, et al.
Publicado: (2026)

Evaluating SAE interpretability without explanations
por: Paulo, Gonçalo, et al.
Publicado: (2025)

PyLO: Towards Accessible Learned Optimizers in PyTorch
por: Janson, Paul, et al.
Publicado: (2025)

Minimal Sufficient Representations for Self-interpretable Deep Neural Networks
por: Tan, Zhiyao, et al.
Publicado: (2026)

AutoScore-Imbalance: An interpretable machine learning tool for development of clinical scores with rare events data
por: Yuan, Han, et al.
Publicado: (2021)

Learning accurate and interpretable tree-based models
por: Balcan, Maria-Florina, et al.
Publicado: (2024)

Bilinear MLPs enable weight-based mechanistic interpretability
por: Pearce, Michael T., et al.
Publicado: (2024)

Learning interpretable positional encodings in transformers depends on initialization
por: Ito, Takuya, et al.
Publicado: (2024)

Domain-Aware Continual Zero-Shot Learning
por: Yi, Kai, et al.
Publicado: (2021)

Incorporating contextual information into KGWAS for interpretable GWAS discovery
por: Jiang, Cheng, et al.
Publicado: (2026)

Towards interpretable AI with quantum annealing feature selection
por: Venturelli, Francesco Aldo, et al.
Publicado: (2026)

Neural Cluster First, Route Second: One-Shot Capacitated Vehicle Routing via Differentiable Optimal Transport
por: Chin, Samuel J. K., et al.
Publicado: (2026)

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
por: Singh, Vaibhav, et al.
Publicado: (2025)

scE2TM improves single-cell embedding interpretability and reveals cellular perturbation signatures
por: Chen, Hegang, et al.
Publicado: (2025)

Optimal algorithmic complexity of inference in quantum kernel methods
por: Gil-Fuster, Elies, et al.
Publicado: (2026)

Topological safeguard for evasion attack interpreting the neural networks' behavior
por: Echeberria-Barrio, Xabier, et al.
Publicado: (2024)

Discovering interpretable models of scientific image data with deep learning
por: Soelistyo, Christopher J., et al.
Publicado: (2024)

Towards eliciting latent knowledge from LLMs with mechanistic interpretability
por: Cywiński, Bartosz, et al.
Publicado: (2025)

From superposition to sparse codes: interpretable representations in neural networks
por: Klindt, David, et al.
Publicado: (2025)

Bayesian neural networks with interpretable priors from Mercer kernels
por: Alberts, Alex, et al.
Publicado: (2025)

Bias-Optimal Bounds for SGD: A Computer-Aided Lyapunov Analysis
por: Cortild, Daniel, et al.
Publicado: (2025)