No article text was recorded for this version.
non-convex optimization gap (convexity assumption gap)
Version 1 of 170 papers72 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Mirror Descent View for Neural Network Quantization
- Blog: The curse of (non)convexity: The case of an Optimization-Inspired Data Pruning algorithm
- Blog: The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
- Blog: Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks
- Blog: Semi-Cyclic Stochastic Gradient Descent
- Blog: Adaptive Gradient-Based Meta-Learning Methods
- Blog: Dynamic Local Regret for Non-convex Online Forecasting
- Blog: Task-Robust Pre-Training for Worst-Case Downstream Adaptation
- Blog: How to beat a Bayesian adversary
- Blog: Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
- Blog: Asynchronous Personalized Federated Learning with Irregular Clients
- Blog: Fine-grained Generalization Analysis of Structured Output Prediction
- Blog: Time Minimization in Hierarchical Federated Learning
- Blog: Asynchronous Distributed Semi-Stochastic Gradient Optimization
- Blog: State Representation Learning Using an Unbalanced Atlas
- Blog: Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent
- Blog: SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization
- Blog: A Convex Duality Framework for GANs
- Blog: Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
- Blog: Accelerating Federated Edge Learning via Optimized Probabilistic Device Scheduling
- Blog: Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence
- Blog: Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure
- Blog: Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networks
- Blog: Convergence Rates for the Stochastic Gradient Descent Method for Non-Convex Objective Functions
- Blog: An Accelerated Method For Decentralized Distributed Stochastic Optimization Over Time-Varying Graphs
- Blog: Faster Federated Learning With Decaying Number of Local SGD Steps
- Blog: Stabilized Proximal-Point Methods for Federated Optimization
- Blog: Learning-to-learn non-convex piecewise-Lipschitz functions
- Blog: Stochastic Learning Under Random Reshuffling With Constant Step-Sizes
- Blog: A Distribution Dependent and Independent Complexity Analysis of Manifold Regularization
- Blog: On the Convergence and Stability of Distributed Sub-model Training
- Blog: Faster Stochastic Algorithms for Minimax Optimization under Polyak-{\L}ojasiewicz Condition
- Blog: High Probability Generalization Bounds with Fast Rates for Minimax Problems
- Blog: When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
- Blog: Characterization of Excess Risk for Locally Strongly Convex Population Risk
- Blog: Simpler Algorithm in Gradient Descent
- Blog: Minimax Pareto Fairness: A Multi Objective Perspective
- Blog: Towards Fair Disentangled Online Learning for Changing Environments
- Blog: Improved Policy Optimization for Online Imitation Learning
- Blog: Multi-Task Deep Learning Games: Investigating Nash Equilibria and Convergence Properties
- Blog: On the Global Optimality of Model-Agnostic Meta-Learning
- Blog: Communication-Efficient Federated Learning with Accelerated Client Gradient
- Blog: Stabilizing Adversarial Nets with Prediction Methods
- Blog: Consistent MetaReg: Alleviating Intra-task Discrepancy for Better Meta-knowledge
- Blog: On the Convergence of FedAvg on Non-IID Data
- Blog: Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond
- Blog: Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks
- Blog: Train on Validation (ToV): Fast data selection with applications to fine-tuning
- Blog: Shifted compression framework: generalizations and improvements
- Blog: Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation
- Blog: Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity
- Blog: Federated Optimization with Doubly Regularized Drift Correction
- Blog: One-Shot Federated Learning for Model Clustering and Learning in Heterogeneous Environments
- Blog: FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
- Blog: Choosing the Sample with Lowest Loss makes SGD Robust
- Blog: Matrix-Free Preconditioning in Online Learning
- Blog: An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization
- Blog: Schedulers for Schedule-free: Theoretically inspired hyperparameters
- Blog: Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
- Blog: Proximal-Based Generative Modeling for Bayesian Inverse Problems
Showing 60 of 70 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_non_convex_optimization_gap_convexity_as_1bb45b62,
title = {non-convex optimization gap (convexity assumption gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-convex-optimization-gap-convexity-assumption-gap/rdr_1bb45b62299d45f7b13627427547efb2},
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_gap_convexity_as_1bb45b62_v1,
title = {non-convex optimization gap (convexity assumption gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-convex-optimization-gap-convexity-assumption-gap/rdr_1bb45b62299d45f7b13627427547efb2/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}