ICLR 2026 accepted papers on Learning theory and algorithms
218 of the 5,358 papers accepted at ICLR 2026 (4.1%) are on Learning theory and algorithms, compared with 4.7% at ICLR 2025. They fall into 9 topics.
See ICLR 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 · 55 papers
- NIMO: a Nonlinear Interpretable MOdel (1 citation)
- Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
- Active Learning for Decision Trees with Provable Guarantees
- AQER: A Scalable and Efficient Data Loader for Digital Quantum Computers
- Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
- Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
- Convex Efficient Coding
- CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
- Data Aware and Scalable Sensitivity Analysis for Decision Tree Ensembles
- Distribution-informed Online Conformal Prediction
- Distributionally Robust Optimization via Generative Ambiguity Modeling
- Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
and 43 more in the interactive map.
Kernels and regression theory · 27 papers
- A Generalized Geometric Theoretical Framework of Centroid Discriminant Analysis for Linear Classification of Multi-dimensional Data
- A Representer Theorem for Hawkes Processes via Penalized Least Squares Minimization
- A Statistical Theory of Overfitting for Imbalanced Classification
- Block-Sample MAC-Bayes Generalization Bounds
- Bound by semanticity: universal laws governing the generalization-identification tradeoff
- Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
- Characterizing and Optimizing the Spatial Kernel of Multi Resolution Hash Encodings
- Deterministic Bounds and Random Estimates of Metric Tensors on Neuromanifolds
- Efficient Estimation of Kernel Surrogate Models for Task Attribution
- On the Bayes Inconsistency of Disagreement Discrepancy Surrogates
- Probabilistic Kernel Function for Fast Angle Testing
- Random-projection ensemble dimension reduction
and 15 more in the interactive map.
Optimal transport · 26 papers
- A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
- Entering the Era of Discrete Diffusion Models: A Benchmark for Schrödinger Bridges and Entropic Optimal Transport
- Fast and Interpretable Protein Substructure Alignment via Optimal Transport
- HOTA: Hamiltonian framework for Optimal Transport Advection
- Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport
- Mixed-Curvature Tree-Sliced Wasserstein Distance
- Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
- On the Wasserstein Geodesic Principal Component Analysis of probability measures
- Optimal transport unlocks end-to-end learning for single-molecule localization
- Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
- Revisiting Tree-Sliced Wasserstein Distance Through the Lens of the Fermat–Weber Problem
- SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples
and 14 more in the interactive map.
Clustering · 24 papers
- Internal Evaluation of Density-Based Clusterings with Noise (1 citation)
- Better Learning-Augmented Spanning Tree Algorithms via Metric Forest Completion
- Distributed Algorithms for Euclidean Clustering
- Metric $k$-clustering using only Weak Comparison Oracles
- Scalable Second-order Riemannian Optimization for $K$-means Clustering
- Sublinear Spectral Clustering Oracle with Little Memory
- Summaries as Centroids for Interpretable and Scalable Text Clustering
- t-SNE Exaggerates Clusters, Provably
- Aligning Collaborative View Recovery and Tensorial Subspace Learning via Latent Representation for Incomplete Multi-View Clustering
- Angle K-Means
- Bridging ML and algorithms: comparison of hyperbolic embeddings
- Confident Block Diagonal Structure-Aware Invariable Graph Completion for Incomplete Multi-view Clustering
and 12 more in the interactive map.
Combinatorial and search optimization · 24 papers
- Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification (1 citation)
- Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP Solvers
- Deep FlexQP: Accelerated Nonlinear Programming via Deep Unfolding
- From Sequential to Parallel: Reformulating Dynamic Programming as GPU Kernels for Large-Scale Stochastic Combinatorial Optimization
- Improving Feasibility via Fast Autoencoder-Based Projections
- Learning to Segment for Vehicle Routing Problems
- Learning to Solve Orienteering Problem with Time Windows and Variable Profits
- Leveraging Discrete Function Decomposability for Scientific Design
- Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers
- Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization
- Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
- Soft Quality-Diversity Optimization
and 12 more in the interactive map.
Sample complexity · 22 papers
- Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample (1 citation)
- Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
- Dimension-Free Decision Calibration for Nonlinear Loss Functions
- How hard is learning to cut? Trade-offs and sample complexity
- Improving Set Function Approximation with Quasi-Arithmetic Neural Networks
- Learning a distance measure from the information-estimation geometry of data
- Mean Estimation from Coarse Data: Characterizations and Efficient Algorithms
- Nearly Space-Optimal Graph and Hypergraph Sparsification in Insertion-Only Data Streams
- Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds
- On the Lipschitz Continuity of Set Aggregation Functions and Neural Networks for Sets
- Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
- Revisiting Active Sequential Prediction-Powered Mean Estimation
and 10 more in the interactive map.
Matrix and tensor methods · 16 papers
- Consistent Low-Rank Approximation
- Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
- Distributionally Robust Linear Regression with Block Lewis Weights
- Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
- Group Representational Position Encoding
- Improved $\ell_{p}$ Regression via Iteratively Reweighted Least Squares
- It's All Just Vectorization: einx, a Universal Notation for Tensor Operations
- On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
- Price of Quality: Sufficient Conditions for Sparse Recovery using Mixed-Quality Data
- Sublinear Time Quantum Algorithm for Attention Approximation
- Subspace Kernel Learning on Tensor Sequences
- The Polar Express: Optimal Matrix Sign Methods and their Application to the Muon Algorithm
and 4 more in the interactive map.
Fairness · 15 papers
- Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
- Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks
- Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching
- Fair Conformal Classification via Learning Representation-Based Groups
- Fair in Mind, Fair in Action? A Synchronous Benchmark for Understanding and Generation in UMLLMs
- A Fair Bayesian Inference through Matched Gibbs Posterior
- Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
- Doubly-Regressing Approach for Subgroup Fairness
- Fair Classification by Direct Intervention on Operating Characteristics
- Fairness via Independence: A General Regularization Framework for Machine Learning
- From Gradient Volume to Shapley Fairness: Towards Fair Multi-Task Learning
- Moving Beyond Medical Exams: A Clinician-Annotated Fairness Dataset of Real-World Tasks and Ambiguity in Mental Healthcare
and 3 more in the interactive map.
Submodular and game algorithms · 9 papers
- Bi-Criteria Metric Distortion
- ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks
- Computing Equilibrium beyond Unilateral Deviation
- General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
- Infinite Horizon Markov Economies
- Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
- Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information
- Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models
- Efficient Submodular Maximization for Sums of Concave over Modular Functions