No article text was recorded for this version.
parameter correlation neglect
Version 1 of 148 papers51 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
- Blog: SSSE: Efficiently Erasing Samples from Trained Machine Learning Models
- Blog: Model-agnostic out-of-distribution detection using combined statistical tests
- Blog: Early Brain Damage
- Blog: Overcoming catastrophic forgetting in neural networks
- Blog: Optimal Brain Damage
- Blog: Adaptive Learning Rate via Covariance Matrix Based Preconditioning for Deep Neural Networks
- Blog: A Unified and General Framework for Continual Learning
- Blog: Fishy: Layerwise Fisher Approximation for Higher-order Neural Network Optimization
- Blog: Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
- Blog: Stochastic Modified Equations and Adaptive Stochastic Gradient Algorithms
- Blog: Fisher SAM: Information Geometry and Sharpness Aware Minimisation
- Blog: Towards Robust Influence Functions with Flat Validation Minima
- Blog: Module-Aware Parameter-Efficient Machine Unlearning on Transformers
- Blog: Fisher kernels for image descriptors: a theoretical overview and experimental results
- Blog: Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
- Blog: HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization
- Blog: Pruning deep neural networks by optimal brain damage
- Blog: Continual Learning through Control Minimization
- Blog: Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
- Blog: Merging Models with Fisher-Weighted Averaging
- Blog: Adaptive Second Order Coresets for Data-efficient Machine Learning
- Blog: A Trace-restricted Kronecker-Factored Approximation to Natural Gradient
- Blog: Model Merging by Uncertainty-Based Gradient Matching
- Blog: Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning
- Blog: Learning Representation from Neural Fisher Kernel with Low-rank Approximation
- Blog: Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure
- Blog: Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization
- Blog: FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
- Blog: Physics of Learning: A Lagrangian perspective to different learning paradigms
- Blog: Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
- Blog: Towards the Limit of Network Quantization
- Blog: Gradients of Functions of Large Matrices
- Blog: Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
- Blog: Fisher SAM: Information Geometry and Sharpness Aware Minimisation
- Blog: Loss-aware Weight Quantization of Deep Networks
- Blog: Sketching curvature for efficient out-of-distribution detection for deep neural networks
- Blog: EVCL: Elastic Variational Continual Learning with Weight Consolidation
- Blog: Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
- Blog: Exploration via Epistemic Value Estimation
- Blog: Lifelong Learning with Sketched Structural Regularization
- Blog: On the Effectiveness of Parameter-Efficient Fine-Tuning
- Blog: GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
- Blog: Data-Dependent Path Normalization in Neural Networks Behnam Neyshabur
- Blog: The Geometry of Forgetting: A Fisher-Information Framework for Alignment-Preserving Continual Adaptation
- Blog: Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator
- Blog: Mirror Descent Algorithms for Minimizing Interacting Free Energy
- Blog: DIDS: Domain Impact-aware Data Sampling for Large Language Model Training
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_parameter_correlation_neglect_60dce182,
title = {parameter correlation neglect},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-correlation-neglect/rdr_60dce182105240e48caa6ff63a7764e5},
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_parameter_correlation_neglect_60dce182_v1,
title = {parameter correlation neglect},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-correlation-neglect/rdr_60dce182105240e48caa6ff63a7764e5/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}