No article text was recorded for this version.
non-convex optimization landscape (optimization landscape complexity)
Version 1 of 11,168 papers1,280 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation
- Blog: Sub-Optimal Local Minima Exist for Almost All Over-parameterized Neural Networks
- Blog: Piecewise Strong Convexity of Neural Networks
- Blog: Trivializing The Energy Landscape Of Deep Networks
- Blog: Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties
- Blog: Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"
- Blog: A convergence analysis of gradient descent for deep linear neural networks
- Blog: Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
- Blog: On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning
- Blog: Spurious local minima in neural networks: a critical view
- Blog: Variance-Reduced Methods for Machine Learning
- Blog: Non-attracting Regions of Local Minima in Deep and Wide Neural Networks
- Blog: Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions
- Blog: Supervised Representation Learning: Transfer Learning with Deep Autoencoders
- Blog: CosNet: A Generalized Spectral Kernel Network
- Blog: Convergence of the Deep BSDE Method for Coupled FBSDEs
- Blog: Learning One Convolutional Layer with Overlapping Patches
- Blog: Holomorphic feedforward networks
- Blog: Les Houches 2022 Special Issue: Editorial
- Blog: Numerical Exploration of Training Loss Level-Sets in Deep Neural Networks
- Blog: Anomalous diffusion dynamics of learning in deep neural networks
- Blog: A Primer on Neural Network Models for Natural Language Processing
- Blog: On Convexity and Linear Mode Connectivity in Neural Networks
- Blog: End-to-End Stochastic Optimization with Energy-Based Model
- Blog: Mollifying Networks
- Blog: Variance-Reduced Methods for Machine Learning
- Blog: The Global Optimization Geometry of Shallow Linear Neural Networks
- Blog: DiffMoog: a Differentiable Modular Synthesizer for Sound Matching
- Blog: Reevaluating Theoretical Analysis Methods for Optimization in Deep Learning
- Blog: Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion
- Blog: Depth Creates No Bad Local Minima
- Blog: Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
- Blog: Convex Formulation of Overparameterized Deep Neural Networks
- Blog: Pansharpening via Detail Injection Based Convolutional Neural Networks
- Blog: Small nonlinearities in activation functions create bad local minima in neural networks
- Blog: A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks
- Blog: The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program
- Blog: Convergence Rates for the Stochastic Gradient Descent Method for Non-Convex Objective Functions
- Blog: A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
- Blog: Mollifying Networks
- Blog: Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
- Blog: Artificial intelligence and its limits
- Blog: Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory
- Blog: Exponentially vanishing sub-optimal local minima in multilayer neural networks
- Blog: Algorithms for solving optimization problems arising from deep neural net models: nonsmooth problems
- Blog: Small nonlinearities in activation functions create bad local minima in neural networks
- Blog: Revealing the Structure of Deep Neural Networks via Convex Duality
- Blog: On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks
- Blog: Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex
- Blog: A phase transition between positional and semantic learning in a solvable model of dot-product attention
- Blog: Revisiting Landscape Analysis in Deep Neural Networks: Eliminating Decreasing Paths to Infinity
- Blog: Learning with Product Units
- Blog: The Global Landscape of Neural Networks: An Overview
- Blog: Deep Learning: An Introduction for Applied Mathematicians
- Blog: Unveiling Privacy Risks in Stochastic Neural Networks Training: Effective Image Reconstruction from Gradients
- Blog: SLAQ: Quality-Driven Scheduling for Distributed Machine Learning
- Blog: Heavy-tailed update distributions arise from information-driven self-organization in nonequilibrium learning
- Blog: A Selective Overview of Deep Learning
- Blog: How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?
- Blog: Learning Graph Weighted Models on Pictures
Showing 60 of 1,168 papers.
History & citation
Current · Permanent link
- Convex Reformulations for Global Neural Network Optimization merged into this direction (100% overlap)
- The Fragility of the Local-is-Global Property in Neural Networks merged into this direction (82% overlap)
- Optimization Strategies for Rugged Neural Loss Landscapes merged into this direction (73% overlap)
- Optimization Landscapes of Residual Networks merged into this direction (64% overlap)
- Global Convergence in Shallow Neural Networks merged into this direction (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_convex_optimization_landscape_optimi_49d7e900,
title = {non-convex optimization landscape (optimization landscape complexity)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-convex-optimization-landscape-optimization-landscape-complexity/rdr_49d7e900e21646afb6f6f4664461de45},
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_non_convex_optimization_landscape_optimi_49d7e900_v1,
title = {non-convex optimization landscape (optimization landscape complexity)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-convex-optimization-landscape-optimization-landscape-complexity/rdr_49d7e900e21646afb6f6f4664461de45/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}