NeurIPS 2024 accepted papers on Learning theory and algorithms
402 of the 4,560 papers accepted at NeurIPS 2024 (8.8%) are on Learning theory and algorithms, compared with 11.9% at NeurIPS 2023. They fall into 9 topics.
See NeurIPS 2024 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 · 92 papers
- shapiq: Shapley Interactions for Machine Learning (13 citations)
- What makes unlearning hard and what to do about it (10 citations)
- Wormhole Loss for Partial Shape Matching (6 citations)
- Active preference learning for ordering items in- and out-of-sample (5 citations)
- Benchmark Data Repositories for Better Benchmarking (5 citations)
- Length Optimization in Conformal Prediction (5 citations)
- Active, anytime-valid risk controlling prediction sets (4 citations)
- DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation (4 citations)
- Is Cross-validation the Gold Standard to Estimate Out-of-sample Model Performance? (4 citations)
- Minimum Entropy Coupling with Bottleneck (4 citations)
- Multi-Label Learning with Stronger Consistency Guarantees (4 citations)
- Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists (3 citations)
and 80 more in the interactive map.
Sample complexity · 84 papers
- The Impact of Initialization on LoRA Finetuning Dynamics (6 citations)
- Stopping Bayesian Optimization with Probabilistic Regret Bounds (5 citations)
- Hardness of Learning Neural Networks under the Manifold Hypothesis (4 citations)
- Dimension-free Private Mean Estimation for Anisotropic Distributions (3 citations)
- Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits (3 citations)
- On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs) (3 citations)
- Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts (3 citations)
- Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning (2 citations)
- Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks (2 citations)
- Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms (2 citations)
- Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation (2 citations)
- Testably Learning Polynomial Threshold Functions (2 citations)
and 72 more in the interactive map.
Kernels and regression theory · 51 papers
- A Unified Recipe for Deriving (Time-Uniform) PAC-Bayes Bounds (6 citations)
- Model Collapse Demystified: The Case of Regression (6 citations)
- A Canonicalization Perspective on Invariant and Equivariant Learning (5 citations)
- Provable and Efficient Dataset Distillation for Kernel Ridge Regression (3 citations)
- Transformers are Minimax Optimal Nonparametric In-Context Learners (3 citations)
- Dimension-free deterministic equivalents and scaling laws for random feature regression (2 citations)
- Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random (2 citations)
- Information-theoretic Generalization Analysis for Expected Calibration Error (2 citations)
- Optimal deep learning of holomorphic operators between Banach spaces (2 citations)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (2 citations)
- Sample-efficient Bayesian Optimisation Using Known Invariances (2 citations)
- Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence (2 citations)
and 39 more in the interactive map.
Combinatorial and search optimization · 50 papers
- UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems (10 citations)
- Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers (9 citations)
- Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes (8 citations)
- MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding (7 citations)
- Learning to compute Gröbner bases (4 citations)
- Are Graph Neural Networks Optimal Approximation Algorithms? (3 citations)
- Are Multiple Instance Learning Algorithms Learnable for Instances? (3 citations)
- Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search (3 citations)
- Neural Krylov Iteration for Accelerating Linear System Solving (3 citations)
- Neural Model Checking (3 citations)
- DistrictNet: Decision-aware learning for geographical districting (2 citations)
- ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks (2 citations)
and 38 more in the interactive map.
Matrix and tensor methods · 39 papers
- Nuclear Norm Regularization for Deep Learning (5 citations)
- Trade-Offs of Diagonal Fisher Information Matrix Estimators (5 citations)
- Adaptive Sampling for Efficient Softmax Approximation (4 citations)
- LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search (4 citations)
- Efficient Leverage Score Sampling for Tensor Train Decomposition (3 citations)
- Nearly Optimal Approximation of Matrix Functions by the Lanczos Method (3 citations)
- Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks (3 citations)
- Block Sparse Bayesian Learning: A Diversified Scheme (2 citations)
- Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts (2 citations)
- Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms (2 citations)
- A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness (1 citation)
- An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling (1 citation)
and 27 more in the interactive map.
Submodular and game algorithms · 26 papers
- Efficiency of the First-Price Auction in the Autobidding World (4 citations)
- Randomized Strategic Facility Location with Predictions (3 citations)
- Motif-oriented influence maximization for viral marketing in large-scale social networks (2 citations)
- No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation (2 citations)
- Sample Complexity of Posted Pricing for a Single Item (2 citations)
- Fair Allocation in Dynamic Mechanism Design (1 citation)
- Fairness and Efficiency in Online Class Matching (1 citation)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (1 citation)
- Learning Optimal Tax Design in Nonatomic Congestion Games (1 citation)
- Learning Social Welfare Functions (1 citation)
- Learning-Augmented Dynamic Submodular Maximization (1 citation)
- Plant-and-Steal: Truthful Fair Allocations via Predictions (1 citation)
and 14 more in the interactive map.
Fairness · 25 papers
- CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence (7 citations)
- Fairness in Social Influence Maximization via Optimal Transport (6 citations)
- Interpolating Item and User Fairness in Multi-Sided Recommendations (4 citations)
- The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning (3 citations)
- A Taxonomy of Challenges to Curating Fair Datasets (2 citations)
- Counterfactual Fairness by Combining Factual and Counterfactual Predictions (2 citations)
- Fair Wasserstein Coresets (2 citations)
- Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness (2 citations)
- Fair Kernel K-Means: from Single Kernel to Multiple Kernel (1 citation)
- FairJob: A Real-World Dataset for Fairness in Online Systems (1 citation)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (1 citation)
- Fairness-Aware Estimation of Graphical Models (1 citation)
and 13 more in the interactive map.
Clustering · 21 papers
- Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence (12 citations)
- Capturing the denoising effect of PCA via compression ratio (4 citations)
- Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering (3 citations)
- Proportional Fairness in Clustering: A Social Choice Perspective (3 citations)
- Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures (2 citations)
- Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering (2 citations)
- From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement (2 citations)
- Proportional Fairness in Non-Centroid Clustering (2 citations)
- Scalable DBSCAN with Random Projections (2 citations)
- The Fairness-Quality Tradeoff in Clustering (2 citations)
- Efficient Centroid-Linkage Clustering (1 citation)
- Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering
and 9 more in the interactive map.
Optimal transport · 14 papers
- Semidefinite Relaxations of the Gromov-Wasserstein Distance (3 citations)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (2 citations)
- Automatic Outlier Rectification via Optimal Transport (2 citations)
- Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling (2 citations)
- Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently (1 citation)
- Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds (1 citation)
- Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
- Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
- Learning Elastic Costs to Shape Monge Displacements
- Light Unbalanced Optimal Transport
- Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
- Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
and 2 more in the interactive map.