No article text was recorded for this version.
optimization landscape complexity
Version 1 of 164 papers83 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Challenges in Training PINNs: A Loss Landscape Perspective
- Blog: Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results
- Blog: Condensation of Force Field Parameters from Machine Learning Predicted Distributions for High-Throughput Virtual Screening Applications
- Blog: Preconditioning for Physics-Informed Neural Networks
- Blog: Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods
- Blog: Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
- Blog: Apprentissage d'algorithmes itératifs pour résoudre des EDPs
- Blog: Characterizing possible failure modes in physics-informed neural networks
- Blog: Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components
- Blog: When physics meets machine learning: a survey of physics-informed machine learning
- Blog: When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning
- Blog: Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
- Blog: Mitigating Gradient Pathology in PINNs through Aligned Constraint
- Blog: Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks
- Blog: Position: Optimization in SciML Should Employ the Function Space Geometry
- Blog: Can Physics-Informed Neural Networks beat the Finite Element Method?
- Blog: Layer Separation Deep Learning Model with Auxiliary Variables for Partial Differential Equations
- Blog: The Challenges of the Nonlinear Regime for Physics-Informed Neural Networks
- Blog: Enhancing Physics-Informed Neural Networks Through Feature Engineering
- Blog: Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing
- Blog: Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method
- Blog: Physics Informed Machine Learning with Misspecified Priors: \\An analysis of Turning Operation in Lathe Machines
- Blog: Convergence Analysis of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
- Blog: Physics-aligned field reconstruction with diffusion bridge
- Blog: VI-PINNs: Variance-involved Physics-informed Neural Networks for Fast and Accurate Prediction of Partial Differential Equations
- Blog: Evaluating Loss Landscapes from a Topology Perspective
- Blog: NH-PINN: Neural homogenization based physics-informed neural network for multiscale problems
- Blog: Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations
- Blog: DDBot: Differentiable Physics-based Digging Robot for Unknown Granular Materials
- Blog: Fast Convergence of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
- Blog: Neural Spectral Methods: Self-supervised learning in the spectral domain
- Blog: JAX-Accelerated Neuroevolution of Physics-informed Neural Networks: Benchmarks and Experimental Results
- Blog: Fast training of accurate physics-informed neural networks without gradient descent
- Blog: ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning
- Blog: Speech dereverberation constrained on room impulse response characteristics
- Blog: Conformal mapping Coordinates Physics-Informed Neural Networks (CoCo-PINNs): learning neural networks for designing neutral inclusions
- Blog: Multi-variance replica exchange SGMCMC for inverse and forward problems via Bayesian PINN
- Blog: PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
- Blog: Adaptive Physics-informed Neural Networks: A Survey
- Blog: PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks
- Blog: Effective Latent Differential Equation Models via Attention and Multiple Shooting
- Blog: Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
- Blog: Can We Use Neural Regularization to Solve Depth Super-Resolution?
- Blog: Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
- Blog: The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators
- Blog: Machine Learning with Physics Knowledge for Prediction: A Survey
- Blog: Learning a Neural Solver for Parametric PDE to Enhance Physics-Informed Methods
- Blog: Physics-Informed Neural Operator for Learning Partial Differential Equations
- Blog: Stably Accelerating Stiff Quantitative Systems Pharmacology Models: Continuous-Time Echo State Networks as Implicit Machine Learning
- Blog: GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
- Blog: Progressive Learning for Physics-informed Neural Motion Planning
- Blog: Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent
- Blog: Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
- Blog: Neural networks enforcing physical symmetries in nonlinear dynamical lattices: The case example of the Ablowitz–Ladik model
- Blog: Learn Singularly Perturbed Solutions via Homotopy Dynamics
- Blog: Adaptive Self-supervision Algorithms for Physics-informed Neural Networks
- Blog: Physics-Informed Neural Networks with Trust-Region Sequential Quadratic Programming
- Blog: RoPINN: Region Optimized Physics-Informed Neural Networks
- Blog: A PINN-enriched finite element method for linear elliptic problems
- Blog: SetPINNs: Set-based Physics-informed Neural Networks
Showing 60 of 64 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_optimization_landscape_complexity_5a923bcb,
title = {optimization landscape complexity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/optimization-landscape-complexity/rdr_5a923bcb4ed0437992fbef550f6fcd6f},
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_optimization_landscape_complexity_5a923bcb_v1,
title = {optimization landscape complexity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/optimization-landscape-complexity/rdr_5a923bcb4ed0437992fbef550f6fcd6f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}