ICML 2025 accepted papers on Learning theory and algorithms
330 of the 3,342 papers accepted at ICML 2025 (9.9%) are on Learning theory and algorithms, compared with 11.6% at ICML 2024. They fall into 9 topics.
See ICML 2025 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 · 96 papers
- AutoEval Done Right: Using Synthetic Data for Model Evaluation (1 citation)
- Learning with Selectively Labeled Data from Multiple Decision-makers (1 citation)
- Leveraging Predictive Equivalence in Decision Trees (1 citation)
- Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space (1 citation)
- Preference learning made easy: Everything should be understood through win rate (1 citation)
- Robust Conformal Outlier Detection under Contaminated Reference Data (1 citation)
- Softmax is not Enough (for Sharp Size Generalisation) (1 citation)
- A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators
- A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
- A Unified Comparative Study with Generalized Conformity Scores for Multi-Output Conformal Regression
- A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
- Algorithms with Calibrated Machine Learning Predictions
and 84 more in the interactive map.
Sample complexity · 49 papers
- Mechanisms of Projective Composition of Diffusion Models (1 citation)
- Phase transitions for the existence of unregularized M-estimators in single index models (1 citation)
- Adaptive Estimation and Learning under Temporal Distribution Shift
- Batch List-Decodable Linear Regression via Higher Moments
- Binary Hypothesis Testing for Softmax Models and Leverage Score Models
- Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
- Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination
- Ehrenfeucht-Haussler Rank and Chain of Thought
- Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
- Exact Upper and Lower Bounds for the Output Distribution of Neural Networks with Random Inputs
- Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
- Generation from Noisy Examples
and 37 more in the interactive map.
Kernels and regression theory · 37 papers
- Adaptive kernel predictors from feature-learning infinite limits of neural networks (1 citation)
- A Bregman Proximal Viewpoint on Neural Operators
- Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
- Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
- Distributionally Robust Active Learning for Gaussian Process Regression
- Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
- From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning
- Function Encoders: A Principled Approach to Transfer Learning in Hilbert Spaces
- Generalization and Robustness of the Tilted Empirical Risk
- Kernel Quantile Embeddings and Associated Probability Metrics
- Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
- Learning with Exact Invariances in Polynomial Time
and 25 more in the interactive map.
Combinatorial and search optimization · 33 papers
- Discrete Neural Algorithmic Reasoning (1 citation)
- Neural Solver Selection for Combinatorial Optimization (1 citation)
- Validating Mechanistic Interpretations: An Axiomatic Approach (1 citation)
- AutoAL: Automated Active Learning with Differentiable Query Strategy Search
- BILBO: BILevel Bayesian Optimization
- Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO*
- Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
- End-to-End Learning Framework for Solving Non-Markovian Optimal Control
- Graph-Based Algorithms for Diverse Similarity Search
- Inverse Optimization via Learning Feasible Regions
- Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?
- Neural Event-Triggered Control with Optimal Scheduling
and 21 more in the interactive map.
Matrix and tensor methods · 32 papers
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (1 citation)
- A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings
- Compact Matrix Quantum Group Equivariant Neural Networks
- Efficient Network Automatic Relevance Determination
- Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
- Fast Tensor Completion via Approximate Richardson Iteration
- Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices
- GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
- Low-Rank Thinning
- MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product
- Model Immunization from a Condition Number Perspective
- Models of Heavy-Tailed Mechanistic Universality
and 20 more in the interactive map.
Clustering · 29 papers
- Almost Optimal Fully Dynamic $k$-Center Clustering with Recourse (1 citation)
- Average Sensitivity of Hierarchical $k$-Median Clustering
- Correlation Clustering Beyond the Pivot Algorithm
- Dynamic Similarity Graph Construction with Kernel Density Estimation
- Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges
- Fair Clustering via Alignment
- Faster Approximation Algorithms for k-Center via Data Reduction
- Generalization Performance of Ensemble Clustering: From Theory to Algorithm
- Learning-Augmented Hierarchical Clustering
- Modified K-means Algorithm with Local Optimality Guarantees
- PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clustering
- Relative Error Fair Clustering in the Weak-Strong Oracle Model
and 17 more in the interactive map.
Submodular and game algorithms · 19 papers
- An Asymptotically Optimal Approximation Algorithm for Multiobjective Submodular Maximization at Scale
- Breaking Barriers: Combinatorial Algorithms for Non-Monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation
- Computing Voting Rules with Improvement Feedback
- Fraud-Proof Revenue Division on Subscription Platforms
- Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
- Improved Theoretically-Grounded Evolutionary Algorithms for Subset Selection with a Linear Cost Constraint
- Optimal Auction Design in the Joint Advertising
- Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies
- Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
- Procurement Auctions via Approximately Optimal Submodular Optimization
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
- The impact of uncertainty on regularized learning in games
and 7 more in the interactive map.
Optimal transport · 18 papers
- Hierarchical Refinement: Optimal Transport to Infinity and Beyond
- Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization
- Lightspeed Geometric Dataset Distance via Sliced Optimal Transport
- On the Private Estimation of Smooth Transport Maps
- Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization
- Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
- TAROT: Targeted Data Selection via Optimal Transport
- Tightening Causal Bounds via Covariate-Aware Optimal Transport
- Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
- Tree-Sliced Wasserstein Distance with Nonlinear Projection
- Tree-Sliced Wasserstein Distance: A Geometric Perspective
and 6 more in the interactive map.
Fairness · 17 papers
- Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies (1 citation)
- Accelerating Spectral Clustering under Fairness Constraints
- Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networks
- CTBench: A Library and Benchmark for Certified Training
- FairICP: Encouraging Equalized Odds via Inverse Conditional Permutation
- Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
- Position: The Categorization of Race in ML is a Flawed Premise
- Preserving AUC Fairness in Learning with Noisy Protected Groups
- Robust ML Auditing using Prior Knowledge
- The Disparate Benefits of Deep Ensembles
- Bridging Fairness and Efficiency in Conformal Inference: A Surrogate-Assisted Group-Clustered Approach
- Disparate Conditional Prediction in Multiclass Classifiers
and 5 more in the interactive map.