ICML 2026 accepted papers on Learning theory and algorithms
395 of the 6,341 papers accepted at ICML 2026 (6.2%) are on Learning theory and algorithms, compared with 9.9% at ICML 2025. They fall into 9 topics.
See ICML 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Prediction and decision losses · 101 papers
- An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems (1 citation)
- Conditional Coverage Diagnostics for Conformal Prediction (1 citation)
- Minimizing Upper Confidence Bounds: A Data-Driven Framework for Stochastic Programming (1 citation)
- Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication (1 citation)
- A Risk Decomposition Framework for Pre-hoc Fine-tuning Prediction
- A Theoretical Framework for Modular Learning of Robust Generative Models
- Adaptive Contracts for Cost-Effective AI Delegation
- Adaptively Robust Resettable Streaming
- AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
- Algorithmic Recourse of In-Context Learning for Tabular Data
- Approximate Nearest Neighbor Search for Modern AI: A Projection-Augmented Graph Approach
- Barriers to Counterfactual Credit Attribution for Autoregressive Models
and 89 more in the interactive map.
Sample complexity · 74 papers
- How High is ‘High’? Rethinking the Roles of Dimensionality in Topological Data Analysis and Manifold Learning (1 citation)
- Learning Junta Distributions, Quantum Junta States, and QAC$^0$ Circuits (1 citation)
- $\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
- A Fine-Grained Understanding of Uniform Convergence for Halfspaces
- A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
- Accelerating Regression Tasks with Quantum Algorithms
- Active Regression for Single-Index Models with Unknown Link Functions
- Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond
- Approximating f -Divergences with Rank Statistics
- Approximation Bounds for Transformer Networks with Application to Regression
- Approximation Error Upper and Lower Bounds for Hölder Class with Transformers
- Asymptotically Optimal Sequential Testing with Markovian Data
and 62 more in the interactive map.
Kernels and regression theory · 55 papers
- Unifying Low Dimensional Spectra in Deep Learning (2 citations)
- A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt
- A Theoretical Framework for Statistical Evaluability of Generative Models
- Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels
- Any-dimensional invariant universality
- Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach
- Asymmetric conformal prediction with penalized kernel sum-of-squares
- Asymptotic Theory of Iterated Empirical Risk Minimization, with Applications to Active Learning
- Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
- Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding
- Fast kernel methods: Sobolev, physics-informed, and additive models
- Feature Bagging Provides Stability
and 43 more in the interactive map.
Combinatorial and search optimization · 36 papers
- RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs (1 citation)
- A Penalty Approach For Differentiation Through Black-box Quadratic Programming Solvers
- A Solver-Free Training Method for Predict-then-Optimize
- Batched First-Order Methods for Parallel LP Solving in MIP
- CAffNet: Hard Constraint-Affine Neural Networks
- Conformal Prediction for Early Stopping in Mixed Integer Optimization
- DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
- Decision-focused Sparse Tangent Portfolio Optimization
- Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning
- Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization
- From Feasible to Practical: Pareto-Optimal Synthesis Planning
- Guaranteed Optimal Compositional Explanations for Neurons
and 24 more in the interactive map.
Clustering · 28 papers
- Active Learning with Low-Rank Structure for Data Selection
- Approximation Preserving Coresets
- Capacitated Fair-Range Clustering: Hardness and Approximation Algorithms
- Fair Transit Stop Placement: A Clustering Perspective and Beyond
- Fast k-means Seeding Under The Manifold Hypothesis
- Quantum Algorithms for Triangle Cut Sparsification
- Simple Algorithms for Bad Triangle Transversals with Applications to Correlation Clustering
- The Catastrophic Failure of *the* k-Means Algorithm in High Dimensions, and How Hartigan's Algorithm Avoids It
- A Consensus Anchor-guided Hypergraph Framework for Incomplete Multi-view Clustering
- Alleviating Observation Bias via Causal-Invariant Meta-Learning for Unbalanced Incomplete Multi-view Clustering
- Asymmetric Multi-View Clustering with Hyperbolic Uncertainty Modeling
- Clustered Influence Functions
and 16 more in the interactive map.
Optimal transport · 27 papers
- AvAtar: Learning to Align via Active Optimal Transport
- Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
- cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transport
- Gromov-Wasserstein at Scale, Beyond Squared Norms
- Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
- ITSPACE: Monotone Gaussian Optimal Transport Updates
- Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets
- Optimal and Scalable MAPF via Multi-Marginal Optimal Transport and Schrödinger Bridges
- Optimal Transport Group Counterfactual Explanations
- Optimal Transport under Group Fairness Constraints
- Partial Identification under High-Dimensional Potential Outcomes and Confounders via Optimal Transport
- Quantifying the noise sensitivity of the Wasserstein metric for images
and 15 more in the interactive map.
Matrix and tensor methods · 27 papers
- An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
- An Exterior Method for Nonnegative Matrix Factorization
- Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
- Combinatorial Sparse PCA Beyond the Spiked Identity Model
- Deep Single-Index Fréchet Regression
- Dual Quaternion SE(3) Synchronization with Recovery Guarantees
- Even Faster Kernel Matrix Linear Algebra via Density Estimation
- Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
- Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
- Grokking Finite-Dimensional Algebra
- Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA
- KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
and 15 more in the interactive map.
Submodular and game algorithms · 26 papers
- A Direct Second-Order Method for Solving Two-Player Zero-Sum Games
- A General Framework for Dynamic Consistent Submodular Maximization
- Adaptive Multi-Round Allocation with Stochastic Arrivals
- Allocating Variance to Maximize Expectation
- Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement Auctions
- Enhancing Affine Maximizer Auctions with Correlation-Aware Payment
- Envy-Free Allocation of Indivisible Goods via Noisy Queries
- Equilibrium Pricing in Oligopolistic Data Markets
- From Welfare to Utility: Generalized Objectives in Budget-Feasible Procurement
- Global Policy-Space Response Oracles for Two-Player Zero-Sum Games
- Knowing Who, Not How Much: Learning-Augmented Mechanisms for Consumer Utility Maximization
- Leaderboard Incentives: Model Rankings under Strategic Post-Training
and 14 more in the interactive map.
Fairness · 21 papers
- Beyond Procedure: Substantive Fairness in Conformal Prediction
- COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs
- Correcting Overparameterization Effects in Fair Empirical Risk Minimization
- Demystifying the Optimal Fair Classifier in Multi-Class Classification
- Desirable Effort Fairness and Optimality Trade-offs in Strategic Learning
- Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
- Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods
- Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off
- Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
- Fairness in Aggregation: Optimal Top-$k$ and Improved Full Ranking
- FairRARI: A Plug and Play Framework for Fairness-Aware PageRank
- Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
and 9 more in the interactive map.