Cover Image

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cloud, Alex, Goldman-Wetzler, Jacob, Wybitul, Evžen, Miller, Joseph, Turner, Alexander Matt
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Distillation Robustifies Unlearning
by: Lee, Bruce W., et al.
Published: (2025)

Access Controls Will Solve the Dual-Use Dilemma
by: Wybitul, Evžen
Published: (2025)

Output Supervision Can Obfuscate the Chain of Thought
by: Drori, Jacob, et al.
Published: (2025)

Recontextualization Mitigates Specification Gaming without Modifying the Specification
by: Azarbal, Ariana, et al.
Published: (2025)

GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
by: Sanderson, Jacob, et al.
Published: (2026)

Axiomatization of Gradient Smoothing in Neural Networks
by: Zhou, Linjiang, et al.
Published: (2024)

Gradient Inversion Attack on Graph Neural Networks
by: Sinha, Divya Anand, et al.
Published: (2024)

GradINN: Gradient Informed Neural Network
by: Aglietti, Filippo, et al.
Published: (2024)

Gradient-Free Training of Quantized Neural Networks
by: Cohen, Noa, et al.
Published: (2024)

SANGRIA: Stacked Autoencoder Neural Networks with Gradient Boosting for Indoor Localization
by: Gufran, Danish, et al.
Published: (2024)

Uncertainty Quantification for Gradient-based Explanations in Neural Networks
by: Mulye, Mihir, et al.
Published: (2024)

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
by: Huang, Haoyu, et al.
Published: (2026)

Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients
by: Wetzel, Sebastian Johann
Published: (2024)

Gradient Flow Convergence Guarantee for General Neural Network Architectures
by: Jakhmola, Yash
Published: (2025)

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
by: Tang, Xuan, et al.
Published: (2025)

Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
by: Wetzel, Sebastian J., et al.
Published: (2024)

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs
by: Shilov, Igor, et al.
Published: (2025)

NeuralGrok: Accelerate Grokking by Neural Gradient Transformation
by: Zhou, Xinyu, et al.
Published: (2025)

Reconstructing Deep Neural Networks: Unleashing the Optimization Potential of Natural Gradient Descent
by: Liu, Weihua, et al.
Published: (2024)

Gradient Regularized Natural Gradients
by: Dash, Satya Prakash, et al.
Published: (2026)

Revisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning
by: Kim, Hoyong, et al.
Published: (2023)

GradientStabilizer:Fix the Norm, Not the Gradient
by: Huang, Tianjin, et al.
Published: (2025)

NeuraLSP: An Efficient and Rigorous Neural Left Singular Subspace Preconditioner for Conjugate Gradient Methods
by: Benanti, Alexander, et al.
Published: (2026)

Neural Network Optimal Power Flow via Energy Gradient Flow and Unified Dynamics
by: Liu, Xuezhi
Published: (2025)

Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks
by: Li, Jinhao, et al.
Published: (2026)

DeepDefense: Layer-Wise Gradient-Feature Alignment for Building Robust Neural Networks
by: Lin, Ci, et al.
Published: (2025)

Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation
by: Montesuma, Eduardo Fernandes, et al.
Published: (2025)

Mitigating Gradient Overlap in Deep Residual Networks with Gradient Normalization for Improved Non-Convex Optimization
by: Yun, Juyoung
Published: (2024)

Consistency Training Helps Stop Sycophancy and Jailbreaks
by: Irpan, Alex, et al.
Published: (2025)

Gradient-Based Program Synthesis with Neurally Interpreted Languages
by: Macfarlane, Matthew V., et al.
Published: (2026)

Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training
by: Ma, Yuhan, et al.
Published: (2024)

LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
by: Kim, Hyunjun
Published: (2026)

Generalized Policy Gradient with History-Aware Decision Transformer for Reliable Routing over Graph Signals
by: Wei, Xing, et al.
Published: (2025)

Representations of Text and Images Align From Layer One
by: Wybitul, Evžen, et al.
Published: (2026)

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
by: Chmiel, Brian, et al.
Published: (2022)

Weight-Entanglement Meets Gradient-Based Neural Architecture Search
by: Sukthanker, Rhea Sanjay, et al.
Published: (2023)

A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks
by: Papadopoulos, Georgios, et al.
Published: (2025)

Cross-Entropy Optimization for Hyperparameter Optimization in Stochastic Gradient-based Approaches to Train Deep Neural Networks
by: Li, Kevin, et al.
Published: (2024)

Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense
by: Zhan, Haoxi, et al.
Published: (2021)

The Reciprocity Gradient
by: Lin, Yue, et al.
Published: (2026)