No article text was recorded for this version.
curvature-aware optimization
Version 1 of 1434 papers507 conceptsfrozen 2026-10-04
Papers in this version
- Blog: DN-ADMM: Distributed Newton ADMM for Multi-agent Optimization
- Blog: PETScML: Second-order solvers for training regression problems in Scientific Machine Learning
- Blog: An Adaptive Memory Multi-Batch L-BFGS Algorithm for Neural Network Training
- Blog: Newton Method-based Subspace Support Vector Data Description
- Blog: Iterative Project Quasi-Newton Algorithm for Training RBM
- Blog: FedNL: Making Newton-Type Methods Applicable to Federated Learning
- Blog: Learning Sigmoid Belief Networks via Monte Carlo Expectation Maximization
- Blog: Adaptive System Optimization Using Random Directions Stochastic Approximation
- Blog: Distributed Second Order Methods with Fast Rates and Compressed Communication
- Blog: Stochastic Gradient Descent with Large Learning Rate
- Blog: Second-Order Policy Gradient Methods for the Linear Quadratic Regulator
- Blog: Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning
- Blog: Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models
- Blog: Solving Convex-Concave Problems with 𝒪(ε-4/7) Second-Order Oracle Complexity
- Blog: Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses
- Blog: Geodesic acceleration and the small-curvature approximation for\n nonlinear least squares
- Blog: Discovery of Unstable Singularities
- Blog: Sparse Approximations with Interior Point Methods
- Blog: Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks
- Blog: Model-Based Reinforcement Learning via Latent-Space Collocation
- Blog: Newton-type Methods for Inference in Higher-Order Markov Random Fields
- Blog: Biological credit assignment through dynamic inversion of feedforward networks
- Blog: HNO: High-Order Numerical Architecture for ODE-Inspired Deep Unfolding Networks
- Blog: Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
- Blog: Analysis and Optimisation of Bellman Residual Errors with Neural Function Approximation
- Blog: Transformers Learn In-Context by Gradient Descent
- Blog: On the Importance of Consistency in Training Deep Neural Networks
- Blog: Fast Newton-CG Method for Batch Learning of Conditional Random Fields
- Blog: Understanding and Improving Optimization in Predictive Coding Networks
- Blog: Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility
- Blog: PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding
- Blog: Second-Order Stochastic Optimization for Machine Learning in Linear Time
- Blog: Proximal Newton-type methods for convex optimization
- Blog: Fast Hierarchical Learning for Few-Shot Object Detection
- Blog: A Gram-Gauss-Newton Method Learning Overparameterized Deep Neural Networks for Regression Problems
- Blog: Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
- Blog: Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
- Blog: Convex optimization based on global lower second-order models
- Blog: Understanding and Improving Optimization in Predictive Coding Networks
- Blog: Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks
- Blog: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers
- Blog: DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers
- Blog: On the (linear) convergence of Generalized Newton Inexact ADMM
- Blog: Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training
- Blog: Fast Second Order Stochastic Backpropagation for Variational Inference
- Blog: Nesterov's Acceleration For Approximate Newton
- Blog: Improving Levenberg-Marquardt Algorithm for Neural Networks
- Blog: The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
- Blog: A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning
- Blog: Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
- Blog: RLEKF: An Optimizer for Deep Potential with Ab Initio Accuracy
- Blog: An Iterative Algorithm for Rescaled Hyperbolic Functions Regression
- Blog: Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
- Blog: Optimizing Costly Functions with Simple Constraints: A Limited-Memory Projected Quasi-Newton Algorithm
- Blog: Distributed Quasi-Newton Method for Multi-Agent Optimization
- Blog: Optimizing Neural Networks with Kronecker-factored Approximate Curvature
- Blog: A Generic Quasi-Newton Algorithm for Faster Gradient-Based Optimization
- Blog: FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods
- Blog: On the Convergence of Continuous Constrained Optimization for Structure Learning
- Blog: Working Set Selection Using Second Order Information for Training Support Vector Machines
Showing 60 of 434 papers.
History & citation
Current · Permanent link
- Efficient Curvature Approximation for Neural Network Training merged into this direction (64% overlap)
- Condition Number Independent Distributed Second Order Optimization merged into this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_curvature_aware_optimization_67e84ca4,
title = {curvature-aware optimization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/curvature-aware-optimization/rdr_67e84ca42f704a41a255a08615279045},
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_aware_optimization_67e84ca4_v1,
title = {curvature-aware optimization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/curvature-aware-optimization/rdr_67e84ca42f704a41a255a08615279045/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}