Deep learning · optimization papers, 2023–2026

Key findings

• Deep learning · optimization fell from 256 papers in 2023 to 240 in 2026, so interest is cooling.
• NeurIPS publishes the most Deep learning · optimization work: 500 papers from 2023 to 2026, 52% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 5 in 2023 to 23 in 2026.
• Among the 11 topics under Deep Learning, it ranks #6 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 0.9x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Achieving Directional-Stationarity from a Single Random Direction Step
• ICML 2026Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning
• ICLR 2026From Sorting Algorithms to Scalable Kernels: Bayesian Optimization in High-Dimensional Permutation Spaces
• CVPR 2026Coverage Optimization for Camera View Selection
• NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
• ICML 2025Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions
• ICLR 2025Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
• CVPR 2025HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
• NeurIPS 2024$\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
• ICML 2024Barrier Algorithms for Constrained Non-Convex Optimization
• ICLR 2024Bayesian Coreset Optimization for Personalized Federated Learning
• CVPR 2024Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization
• NeurIPS 2023$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
• ICML 2023Buying Information for Stochastic Optimization
• ICLR 2023Alternating Differentiation for Optimization Layers
• CVPR 2023Visual-Language Prompt Tuning With Knowledge-Guided Context Optimization
• NeurIPS 2026Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
• ICML 2026Riemannian Optimization for Fair Spectral Clustering
• ICLR 2026Gradient-Based Diversity Optimization with Differentiable Top-$k$ Objective
• CVPR 2026Its Never Too Late Noise Optimization for Collapse Recovery in

All Deep learning · optimization papers

163 papers, page 3 of 4

101. ICML 2025TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization
102. NeurIPS 2025A Beyond-Worst-Case Analysis of Greedy k-means++
103. NeurIPS 2025A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization
104. NeurIPS 2025A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
105. NeurIPS 2025An Ellipsoid Algorithm for Online Convex Optimization
106. NeurIPS 2025Auto-Connect: Connectivity-Preserving RigFormer with Direct Preference Optimization
107. NeurIPS 2025Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation
108. NeurIPS 2025Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
109. NeurIPS 2025Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
110. NeurIPS 2025Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
111. NeurIPS 2025BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization
112. NeurIPS 2025Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization
113. NeurIPS 2025Continuous Subspace Optimization for Continual Learning
114. NeurIPS 2025Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
115. NeurIPS 2025Convergence Rates of Constrained Expected Improvement
116. NeurIPS 2025Differentiable extensions with rounding guarantees for combinatorial optimization over permutations
117. NeurIPS 2025Enhancing Training Data Attribution with Representational Optimization
118. NeurIPS 2025Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
119. NeurIPS 2025Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
120. NeurIPS 2025Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set
121. NeurIPS 2025Flat Channels to Infinity in Neural Loss Landscapes
122. NeurIPS 2025FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
123. NeurIPS 2025Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
124. NeurIPS 2025HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
125. NeurIPS 2025High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
126. NeurIPS 2025KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
127. NeurIPS 2025Learn2Mix: Training Neural Networks Using Adaptive Data Integration
128. NeurIPS 2025Learning (Approximately) Equivariant Networks via Constrained Optimization
129. NeurIPS 2025Learning Theory for Kernel Bilevel Optimization
130. NeurIPS 2025Leveraging robust optimization for llm alignment under distribution shifts
131. NeurIPS 2025MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
132. NeurIPS 2025Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
133. NeurIPS 2025Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization
134. NeurIPS 2025On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
135. NeurIPS 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
136. NeurIPS 2025On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
137. NeurIPS 2025Online Optimization for Offline Safe Reinforcement Learning
138. NeurIPS 2025Partial Correlation Network Estimation by Semismooth Newton Methods
139. NeurIPS 2025PDPO: Parametric Density Path Optimization
140. NeurIPS 2025Preference Optimization by Estimating the Ratio of the Data Distribution
141. NeurIPS 2025Probing Neural Combinatorial Optimization Models
142. NeurIPS 2025Problem-Parameter-Free Decentralized Bilevel Optimization
143. NeurIPS 2025Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO
144. NeurIPS 2025Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
145. NeurIPS 2025Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
146. NeurIPS 2025Revisiting Frank-Wolfe for Structured Nonconvex Optimization
147. NeurIPS 2025Robust Hyperbolic Learning with Curvature-Aware Optimization
148. NeurIPS 2025Scalable inference of functional neural connectivity at submillisecond timescales
149. NeurIPS 2025Semi-infinite Nonconvex Constrained Min-Max Optimization
150. NeurIPS 2025Sequential Monte Carlo for Policy Optimization in Continuous POMDPs

FAQ

How many Deep learning · optimization papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

953 in total: 256 in 2023, 294 in 2024, 163 in 2025, 240 in 2026.

How many Deep learning · optimization papers are at NeurIPS 2026?

NeurIPS 2026 has 103 Deep learning · optimization papers, versus 62 the year before.

How many Deep learning · optimization papers are at ICLR 2026?

ICLR 2026 has 44 Deep learning · optimization papers, versus 51 the year before.

How many Deep learning · optimization papers are at ICML 2026?

ICML 2026 has 86 Deep learning · optimization papers, versus 44 the year before.

How many Deep learning · optimization papers are at CVPR 2026?

CVPR 2026 has 7 Deep learning · optimization papers, versus 6 the year before.

Which conference publishes the most Deep learning · optimization papers?

NeurIPS, with 500 papers from 2023 to 2026.