Nonconvex Optimization papers, 2023–2026

Key findings

• Nonconvex Optimization went from 346 papers in 2023 to 757 in 2026, roughly 2.2x in three years.
• NeurIPS publishes the most Nonconvex Optimization work: 958 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 2 in 2023 to 44 in 2026.
• Among the 5 topics under Optimization and Scaling, it ranks #2 by 2026 paper count; the fastest grower in the group, Scaling Laws, is up 4.1x versus 2.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026$\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions
• ICML 2026$\texttt{MetaDistill}$: Unlocking the Performance Ceiling for Pretrained Optimizers
• ICLR 2026Behavioral Embeddings of Programs: A Quasi-Dynamic Approach for Optimization Prediction
• CVPR 2026Coverage Optimization for Camera View Selection
• NeurIPS 2025Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
• ICML 2025A Bregman Proximal Viewpoint on Neural Operators
• ICLR 2025A Truncated Newton Method for Optimal Transport
• CVPR 2025Balanced Rate-Distortion Optimization in Learned Image Compression
• NeurIPS 2024A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
• ICML 2024A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization
• ICLR 2024Bayesian Coreset Optimization for Personalized Federated Learning
• CVPR 2024FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance
• NeurIPS 2023A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
• ICML 2023A Distribution Optimization Framework for Confidence Bounds of Risk Measures
• ICLR 2023A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
• CVPR 2023Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization
• NeurIPS 2026A Doubly Smoothed Decentralized Stochastic Minimax Optimization Algorithm
• ICML 2026A Constrained Optimization Perspective of Unrolled Transformers
• ICLR 2026BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
• CVPR 2026Fully Decentralized Certified Unlearning

All Nonconvex Optimization papers

250 papers, page 4 of 5

151. NeurIPS 2026Optimal Hidden-Target Learning for Online Inventory Optimization on General Convex Sets
152. NeurIPS 2026Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
153. NeurIPS 2026Ordered Policy Optimization
154. NeurIPS 2026Orthogonal Updates for the Win: Towards Accelerated Adaptive Minimax Optimization
155. NeurIPS 2026PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization
156. NeurIPS 2026PACO: Partial-order-Augmented Continuous Optimization for Differentiable Causal Discovery
157. NeurIPS 2026Pairwise AUC Optimization Needs Corrective Power: A Unified View
158. NeurIPS 2026Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
159. NeurIPS 2026ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization
160. NeurIPS 2026Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning
161. NeurIPS 2026Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
162. NeurIPS 2026PISG: Constraint-Aligned Signal Amplification for Diffusion-Based Combinatorial Optimization
163. NeurIPS 2026Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions
164. NeurIPS 2026POME: Post Optimization Model Edit via Muon-Style Projection
165. NeurIPS 2026Position: Lottery Tickets Do Not Explain Overparameterization. How About Escape Dimensions?
166. NeurIPS 2026Posterior Alternative Calibration in Ambiguous Inverse Problems
167. NeurIPS 2026Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
168. NeurIPS 2026Principled Policy Optimization for LLMs via Self-Normalized Importance Sampling
169. NeurIPS 2026Quality-Diversity Optimization as Multi-Objective Optimization
170. NeurIPS 2026Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
171. NeurIPS 2026Randomized Kriging Believer For Parallel Bayesian Optimization With Regret Bounds
172. NeurIPS 2026Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
173. NeurIPS 2026Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization
174. NeurIPS 2026Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias
175. NeurIPS 2026Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
176. NeurIPS 2026Regularization Paths for Continuous DAG Learning
177. NeurIPS 2026Regularized Large Neighborhood Search
178. NeurIPS 2026Reinforcement Learning for Code Optimization
179. NeurIPS 2026Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
180. NeurIPS 2026ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
181. NeurIPS 2026Rennala-NSGD: Asynchronous Stochastic Optimization Beyond Euclidean Geometry
182. NeurIPS 2026Replay-buffer engineering for noise-robust quantum circuit optimization
183. NeurIPS 2026RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
184. NeurIPS 2026Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity
185. NeurIPS 2026Rethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
186. NeurIPS 2026Rethinking Gradient Approximation in Quantization: A Zeroth-Order Expectation Perspective
187. NeurIPS 2026Rethinking Language Model Scaling under Transferable Hypersphere Optimization
188. NeurIPS 2026Revisiting Decentralized Online Convex Optimization with Compressed Communication
189. NeurIPS 2026Riemannian Bilevel Optimization under the Polyak–Łojasiewicz Condition
190. NeurIPS 2026Riemannian Lyapunov Framework: Optimization as Closed-Loop Control on Riemannian Manifolds
191. NeurIPS 2026Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
192. NeurIPS 2026Robust Latent Space Bayesian Optimization with Marginalized Kernel
193. NeurIPS 2026Robust Noisy Inductive Matrix Completion with Local Linear Convergence
194. NeurIPS 2026Robust Policy Optimization to Prevent Catastrophic Forgetting
195. NeurIPS 2026ROCKET: Rapid Optimization via Calibration-guided Knapsack-Enhanced Truncation for Efficient Model Compression
196. NeurIPS 2026RxnOptBench: Benchmarking LLMs for Reaction-Condition Optimization in Organic Methodology
197. NeurIPS 2026Sample complexity of stochastic optimization with integer variables
198. NeurIPS 2026Sample-Efficient Optimization over Generative Priors via Coarse Learnability
199. NeurIPS 2026SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
200. NeurIPS 2026Scalable Distributed Stochastic Optimization via Bidirectional Compression: Beyond Pessimistic Limits

FAQ

How many Nonconvex Optimization papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,330 in total: 346 in 2023, 560 in 2024, 667 in 2025, 757 in 2026.

How many Nonconvex Optimization papers are at NeurIPS 2026?

NeurIPS 2026 has 250 Nonconvex Optimization papers, versus 279 the year before.

How many Nonconvex Optimization papers are at ICLR 2026?

ICLR 2026 has 178 Nonconvex Optimization papers, versus 177 the year before.

How many Nonconvex Optimization papers are at ICML 2026?

ICML 2026 has 286 Nonconvex Optimization papers, versus 192 the year before.

How many Nonconvex Optimization papers are at CVPR 2026?

CVPR 2026 has 43 Nonconvex Optimization papers, versus 19 the year before.

Which conference publishes the most Nonconvex Optimization papers?

NeurIPS, with 958 papers from 2023 to 2026.