Research map

Learning theory and algorithms: research map

Sample complexity, kernels, fairness, clustering, optimal transport and algorithmic ML.

9,722 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 9 topics. Within all five venues, its share shrank from 8.4% in 2023–24 to 5.3% in 2025–26 (2,231 → 2,430 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Learning theory and algorithms in the interactive map

Topics

• Prediction and decision losses · 2,134 papers
  Active learning and subset selection, Adaptive testing and experiments, Distributionally robust optimization
• Combinatorial and search optimization · 1,492 papers
  Constrained neural network optimization, Unsupervised neural combinatorial optimization, Decision-focused optimization
• Sample complexity · 1,363 papers
  Minimax estimation rates, Optimal mean estimation and subsampling, Density and property estimation
• Matrix and tensor methods · 1,074 papers
  Low-rank approximation theory, Matrix completion and factorization, Randomized sketching for matrices
• Submodular and game algorithms · 1,030 papers
  Matching markets and welfare, Learned auction design, Fair division of indivisible goods
• Kernels and regression theory · 1,004 papers
  RKHS kernel methods, Neural tangent kernel analysis, Kernel regression under shift
• Clustering · 725 papers
  Clustering approximation algorithms, Correlation clustering, Subspace clustering
• Fairness · 516 papers
  Fairness-constrained classification, Post-processing and transport for fairness, Fair allocation and selection
• Optimal transport · 384 papers
  Neural optimal transport, Transport map estimation, Sinkhorn and entropic OT algorithms

Most cited papers in Learning theory and algorithms

• LightGBM: A Highly Efficient Gradient Boosting Decision Tree (NeurIPS 2017 · 9,433 citations)
• Axiomatic Attribution for Deep Networks (ICML 2017 · 2,911 citations)
• Designing Network Design Spaces (CVPR 2020 · 1,958 citations)
• Understanding Black-box Predictions via Influence Functions (ICML 2017 · 1,328 citations)
• CatBoost: unbiased boosting with categorical features (NeurIPS 2018 · 1,125 citations)
• Counterfactual Fairness (NeurIPS 2017 · 842 citations)
• Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization (CVPR 2016 · 556 citations)
• Superpixels and Polygons Using Simple Non-Iterative Clustering (CVPR 2017 · 496 citations)
• Exploring Generalization in Deep Learning (NeurIPS 2017 · 450 citations)
• The Expressive Power of Neural Networks: A View from the Width (NeurIPS 2017 · 424 citations)
• Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit (CVPR 2016 · 394 citations)
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness (ICML 2018 · 383 citations)