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

159 papers, page 2 of 4

51. ICLR 2025Aioli: A Unified Optimization Framework for Language Model Data Mixing
52. ICLR 2025An Effective Manifold-based Optimization Method for Distributionally Robust Classification
53. ICLR 2025Approximation algorithms for combinatorial optimization with predictions
54. ICLR 2025Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems
55. ICLR 2025Bootstrapping Language Models with DPO Implicit Rewards
56. ICLR 2025Cauchy-Schwarz Regularizers
57. ICLR 2025Convex Formulations for Training Two-Layer ReLU Neural Networks
58. ICLR 2025Decentralized Optimization with Coupled Constraints
59. ICLR 2025Edge-aware Image Smoothing with Relative Wavelet Domain Representation
60. ICLR 2025Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions
61. ICLR 2025FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
62. ICLR 2025Gradient correlation is a key ingredient to accelerate SGD with momentum
63. ICLR 2025Gradient descent with generalized Newton’s method
64. ICLR 2025How Does Critical Batch Size Scale in Pre-training?
65. ICLR 2025Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization
66. ICLR 2025LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace
67. ICLR 2025Latent Bayesian Optimization via Autoregressive Normalizing Flows
68. ICLR 2025Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling
69. ICLR 2025Neural Exploratory Landscape Analysis for Meta-Black-Box-Optimization
70. ICLR 2025Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation
71. ICLR 2025Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping
72. ICLR 2025On the Almost Sure Convergence of the Stochastic Three Points Algorithm
73. ICLR 2025OPTAMI: Global Superlinear Convergence of High-order Methods
74. ICLR 2025Optimizing importance weighting in the presence of sub-population shifts
75. ICLR 2025Optimizing Neural Network Representations of Boolean Networks
76. ICLR 2025Optimizing Posterior Samples for Bayesian Optimization via Rootfinding
77. ICLR 2025Overcoming Lower-Level Constraints in Bilevel Optimization: A Novel Approach with Regularized Gap Functions
78. ICLR 2025Pareto Prompt Optimization
79. ICLR 2025ParFam -- (Neural Guided) Symbolic Regression via Continuous Global Optimization
80. ICLR 2025qNBO: quasi-Newton Meets Bilevel Optimization
81. ICLR 2025Revisiting Large-Scale Non-convex Distributionally Robust Optimization
82. ICLR 2025Second-Order Min-Max Optimization with Lazy Hessians
83. ICLR 2025Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization
84. ICLR 2025The AdEMAMix Optimizer: Better, Faster, Older
85. ICLR 2025The Complexity of Two-Team Polymatrix Games with Independent Adversaries
86. ICLR 2025The Crucial Role of Samplers in Online Direct Preference Optimization
87. ICLR 2025The Directionality of Optimization Trajectories in Neural Networks
88. ICLR 2025To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
89. ICLR 2025Towards Faster Decentralized Stochastic Optimization with Communication Compression
90. ICLR 2025Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
91. ICLR 2025Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
92. ICLR 2025Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
93. ICLR 2025Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
94. ICLR 2025Weighted-Reward Preference Optimization for Implicit Model Fusion
95. ICLR 2025Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
96. ICLR 2024A Discretization Framework for Robust Contextual Stochastic Optimization
97. ICLR 2024A Precise Characterization of SGD Stability Using Loss Surface Geometry
98. ICLR 2024Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise
99. ICLR 2024Accelerating Sinkhorn algorithm with sparse Newton iterations
100. ICLR 2024Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

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.