No article text was recorded for this version.
ill-conditioned optimization
Version 1 of 1196 papers198 conceptsfrozen 2026-10-04
Papers in this version
- Blog: NEO: NEuro-Inspired Optimization—A Fractional Time Series Approach
- Blog: Regularized Barzilai-Borwein method
- Blog: Iterative Project Quasi-Newton Algorithm for Training RBM
- Blog: Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
- Blog: Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
- Blog: Information-Theoretic Perspectives on Optimizers
- Blog: Experimental Comparisons of Derivative Free Optimization Algorithms
- Blog: A Fast Anderson-Chebyshev Acceleration for Nonlinear Optimization
- Blog: New subspace minimization conjugate gradient methods based on regularization model for unconstrained optimization
- Blog: Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
- Blog: TRSVR: An Adaptive Stochastic Trust-Region Method with Variance Reduction
- Blog: Primal-Dual Sequential Subspace Optimization for Saddle-point Problems
- Blog: SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning
- Blog: Second-Order Policy Gradient Methods for the Linear Quadratic Regulator
- Blog: Temporal Difference Learning: Why It Can Be Fast and How It Will Be Faster
- Blog: RES: Regularized Stochastic BFGS Algorithm
- Blog: Understanding Short-Horizon Bias in Stochastic Meta-Optimization
- Blog: Estimate Sequences for Stochastic Composite Optimization: Variance Reduction, Acceleration, and Robustness to Noise
- Blog: A Mini-Block Natural Gradient Method for Deep Neural Networks
- Blog: Scaling Laws for the Principled Design, Initialization, and Preconditioning of ReLU Networks
- Blog: Small Steps and Giant Leaps: Minimal Newton Solvers for Deep Learning
- Blog: Quality Gain Analysis of the Weighted Recombination Evolution Strategy on General Convex Quadratic Functions
- Blog: Gradient Methods with Online Scaling
- Blog: Acceleration of SVRG and Katyusha X by Inexact Preconditioning
- Blog: New perspectives on the natural gradient method
- Blog: Second-Order Optimization with Lazy Hessians
- Blog: Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation
- Blog: Analysis of the Optimization Landscapes for Overcomplete Representation Learning
- Blog: Acceleration in First Order Quasi-strongly Convex Optimization by ODE Discretization
- Blog: L-SR1: Learned Symmetric-Rank-One Preconditioning
- Blog: The Variational Predictive Natural Gradient
- Blog: Regularized linear autoencoders recover the principal components, eventually
- Blog: A Quantum Field Theory of Representation Learning
- Blog: Sparse Approximations with Interior Point Methods
- Blog: Analysis of a natural gradient algorithm on monotonic convex-quadratic-composite functions
- Blog: Policy Newton Algorithm in Reproducing Kernel Hilbert Space
- Blog: A Conservation Law Method in Optimization
- Blog: Curvature-Exploiting Acceleration of Elastic Net Computations
- Blog: Toward Efficient Gradient-Based Value Estimation
- Blog: PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates
- Blog: Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Models
- Blog: An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
- Blog: Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
- Blog: Singular Value Perturbation and Deep Network Optimization
- Blog: Stochastic Damped L-BFGS with Controlled Norm of the Hessian Approximation
- Blog: Accelerating Level-Value Adjustment for the Polyak Stepsize
- Blog: Gradientless Descent: High-Dimensional Zeroth-Order Optimization
- Blog: Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines
- Blog: Improving Optimization in Models With Continuous Symmetry Breaking
- Blog: Newton-type Methods for Minimax Optimization
- Blog: Accelerating Continuous Variable Coherent Ising Machines via Momentum
- Blog: Attention-oriented Brain Storm Optimization for Multimodal Optimization Problems
- Blog: Qualitatively characterizing neural network optimization problems
- Blog: SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
- Blog: RMSProp and equilibrated adaptive learning rates for non-convex optimization
- Blog: An Anderson-Chebyshev Mixing Method for Nonlinear Optimization
- Blog: Fractional Order Distributed Optimization
- Blog: Generalized Polyak Step Size for First Order Optimization with Momentum
- Blog: Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
- Blog: An accelerated variance reducing stochastic method with Douglas-Rachford splitting
Showing 60 of 196 papers.
History & citation
Current · Permanent link
- This direction split from Navigating Ill-Conditioned Loss Landscapes in Deep Learning (80% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_ill_conditioned_optimization_40676779,
title = {ill-conditioned optimization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/ill-conditioned-optimization/rdr_40676779ef3f4b22ab4001af278ac2b4},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_ill_conditioned_optimization_40676779_v1,
title = {ill-conditioned optimization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/ill-conditioned-optimization/rdr_40676779ef3f4b22ab4001af278ac2b4/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}