No article text was recorded for this version.
first-order model linearization
Version 1 of 198 papers110 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
- Blog: Fast Adaptation with Linearized Neural Networks
- Blog: LANA: Latency Aware Network Acceleration
- Blog: LQF: Linear Quadratic Fine-Tuning
- Blog: Lazy Estimation of Variable Importance for Large Neural Networks
- Blog: Local Linear Approximation Algorithm for Neural Network
- Blog: Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence
- Blog: Uncertainty Quantification with the Empirical Neural Tangent Kernel
- Blog: Rethinking Neural-based Matrix Inversion: Why can't, and Where can
- Blog: Model Merging by Output-Space Projection
- Blog: Lazy Estimation of Variable Importance for Large Neural Networks
- Blog: Tangent Transformers for Composition,Privacy and Removal
- Blog: Six Lectures on Linearized Neural Networks
- Blog: Forgettable Federated Linear Learning with Certified Data Removal
- Blog: Personalized Privacy Auditing and Optimization at Test Time
- Blog: Tractable Function-Space Variational Inference in Bayesian Neural Networks
- Blog: Tangent Model Composition for Ensembling and Continual Fine-tuning
- Blog: The fine print on tempered posteriors
- Blog: DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning
- Blog: Accountability Attribution: Tracing Model Behavior to Training Processes
- Blog: Streaming Bayesian Deep Tensor Factorization
- Blog: Linearized two-layers neural networks in high dimension
- Blog: Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
- Blog: Predicting Training Time Without Training
- Blog: On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures
- Blog: Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
- Blog: Approximate Bayesian Optimisation for Neural Networks
- Blog: Cold Posteriors through PAC-Bayes
- Blog: FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems
- Blog: Learning to Solve Inverse Problems for Perceptual Sound Matching
- Blog: Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities
- Blog: Efficient Noise Calculation in Deep Learning-based MRI Reconstructions
- Blog: Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
- Blog: Data Minimization at Inference Time
- Blog: An Adversarial Attacker for Neural Networks in Regression Problems
- Blog: Gradients as Features for Deep Representation Learning
- Blog: Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations
- Blog: Forgettable Federated Linear Learning with Certified Data Removal
- Blog: Dualing GANs
- Blog: Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
- Blog: Improving predictions of Bayesian neural nets via local linearization
- Blog: Observable Propagation: A Data-Efficient Approach to Uncover Feature Vectors in Transformers
- Blog: Linear Relational Decoding of Morphology in Language Models
- Blog: The Dynamics of Gradient Descent for Overparametrized Neural Networks
- Blog: Predicting the Generalization Gap in Deep Networks with Margin Distributions
- Blog: Tangent Transformers for Composition, Privacy and Removal
- Blog: Analytical Moment Regularizer for Gaussian Robust Networks
- Blog: Decoupling the Layers in Residual Networks
- Blog: Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
- Blog: Learning and Generalization in RNNs
- Blog: Predicting the Generalization Gap in Deep Networks with Margin Distributions
- Blog: Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
- Blog: Learning Deep Neural Networks by Iterative Linearisation
- Blog: Scalable computation of prediction intervals for neural networks via matrix sketching
- Blog: Efficient Noise Calculation in Deep Learning-based MRI Reconstructions
- Blog: LQF: Linear Quadratic Fine-Tuning
- Blog: Neural Lineage
- Blog: TRAK: Attributing Model Behavior at Scale
- Blog: Scalable Initial State Interdiction for Factored MDPs
- Blog: Feature learning and random features in standard finite-width convolutional neural networks: An empirical study
Showing 60 of 98 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_first_order_model_linearization_5fda6f0c,
title = {first-order model linearization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/first-order-model-linearization/rdr_5fda6f0c2fc1456481bab6fcf6266613},
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_first_order_model_linearization_5fda6f0c_v1,
title = {first-order model linearization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/first-order-model-linearization/rdr_5fda6f0c2fc1456481bab6fcf6266613/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}