No article text was recorded for this version.
curvature-informed pruning
Version 1 of 135 papers46 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Hessian-Aware Pruning and Optimal Neural Implant
- Blog: SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
- Blog: Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
- Blog: AdaDARE-gamma: Balancing Stability and Plasticity in Multi-modal LLMs through Efficient Adaptation
- Blog: Pruning deep neural networks by optimal brain damage
- Blog: FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server
- Blog: SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot
- Blog: Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
- Blog: AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices
- Blog: Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
- Blog: The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
- Blog: PyHessian: Neural Networks Through the Lens of the Hessian
- Blog: Neural Pruning via Growing Regularization
- Blog: MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
- Blog: Second Order Derivatives for Network Pruning: Optimal Brain Surgeon
- Blog: MSQ: Memory-Efficient Bit Sparsification Quantization
- Blog: WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
- Blog: Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network
- Blog: A Second-Order Perspective on Pruning at Initialization and Knowledge Transfer
- Blog: Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization
- Blog: Global Vision Transformer Pruning with Hessian-Aware Saliency
- Blog: SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization
- Blog: Node Splitting: A Constructive Algorithm for Feed-Forward Neural Networks
- Blog: Search for Efficient Large Language Models
- Blog: Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory
- Blog: DarwinLM: Evolutionary Structured Pruning of Large Language Models
- Blog: The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
- Blog: MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization
- Blog: VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores
- Blog: Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression
- Blog: SWIM: Selective Write-Verify for Computing-in-Memory Neural Accelerators
- Blog: The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models
- Blog: Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives
- Blog: ZipLM: Inference-Aware Structured Pruning of Language Models
- Blog: EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis
History & citation
Current · Permanent link
- This direction split from Hessian Aware Neural Network Pruning (77% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_curvature_informed_pruning_14631413,
title = {curvature-informed pruning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/curvature-informed-pruning/rdr_14631413b73c45639627910b2e9d234e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_curvature_informed_pruning_14631413_v1,
title = {curvature-informed pruning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/curvature-informed-pruning/rdr_14631413b73c45639627910b2e9d234e/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}