ICLR 2024 accepted papers on Learning theory and algorithms
130 of the 2,259 papers accepted at ICLR 2024 (5.8%) are on Learning theory and algorithms, compared with 7.8% at ICLR 2023. They fall into 9 topics.
See ICLR 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 · 27 papers
- Conformal Risk Control (26 citations)
- Topological data analysis on noisy quantum computers (12 citations)
- Data Debugging with Shapley Importance over Machine Learning Pipelines (8 citations)
- Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization (7 citations)
- Leave-one-out Distinguishability in Machine Learning (4 citations)
- Improving equilibrium propagation without weight symmetry through Jacobian homeostasis (2 citations)
- Leveraging Uncertainty Estimates To Improve Classifier Performance (2 citations)
- Non-Exchangeable Conformal Risk Control (2 citations)
- Understanding Certified Training with Interval Bound Propagation (2 citations)
- Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation (1 citation)
- Mean Field Theory in Deep Metric Learning (1 citation)
- Querying Easily Flip-flopped Samples for Deep Active Learning (1 citation)
and 15 more in the interactive map.
Kernels and regression theory · 27 papers
- PINNACLE: PINN Adaptive ColLocation and Experimental points selection (6 citations)
- Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking (2 citations)
- Quadratic models for understanding catapult dynamics of neural networks (2 citations)
- Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data (2 citations)
- Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing (2 citations)
- An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression (1 citation)
- Fantastic Generalization Measures are Nowhere to be Found (1 citation)
- How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression? (1 citation)
- The optimality of kernel classifiers in Sobolev space (1 citation)
- Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression (1 citation)
- A path-norm toolkit for modern networks: consequences, promises and challenges
- Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
and 15 more in the interactive map.
Combinatorial and search optimization · 17 papers
- Guaranteed Approximation Bounds for Mixed-Precision Neural Operators (4 citations)
- Retro-fallback: retrosynthetic planning in an uncertain world (4 citations)
- CoLiDE: Concomitant Linear DAG Estimation (1 citation)
- Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance
- Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
- Near-Optimal Solutions of Constrained Learning Problems
- Neur2RO: Neural Two-Stage Robust Optimization
- The Update-Equivalence Framework for Decision-Time Planning
- Active Retrosynthetic Planning Aware of Route Quality
- Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping
- L2P-MIP: Learning to Presolve for Mixed Integer Programming
- Learning to Solve Bilevel Programs with Binary Tender
and 5 more in the interactive map.
Sample complexity · 17 papers
- Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants (1 citation)
- Estimating Shape Distances on Neural Representations with Limited Samples (1 citation)
- Improved algorithm and bounds for successive projection (1 citation)
- Learning Hierarchical Polynomials with Three-Layer Neural Networks (1 citation)
- Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift (1 citation)
- Optimal Sample Complexity for Average Reward Markov Decision Processes (1 citation)
- Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs (1 citation)
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks (1 citation)
- Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts (1 citation)
- An Efficient Tester-Learner for Halfspaces
- Improved Active Learning via Dependent Leverage Score Sampling
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
and 5 more in the interactive map.
Fairness · 14 papers
- FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling (5 citations)
- FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods (4 citations)
- Unprocessing Seven Years of Algorithmic Fairness (4 citations)
- Post-hoc bias scoring is optimal for fair classification (2 citations)
- fairret: a Framework for Differentiable Fairness Regularization Terms (1 citation)
- Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
- Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
- Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
- f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization
- Fair Classifiers that Abstain without Harm
- On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
- Procedural Fairness Through Decoupling Objectionable Data Generating Components
and 2 more in the interactive map.
Matrix and tensor methods · 10 papers
- HyperAttention: Long-context Attention in Near-Linear Time (9 citations)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (3 citations)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (1 citation)
- How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation (1 citation)
- What's in a Prior? Learned Proximal Networks for Inverse Problems (1 citation)
- Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers
- Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
- Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model
- Global Optimality for Non-linear Constrained Restoration Problems via Invexity
- Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice
Optimal transport · 9 papers
- Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs (5 citations)
- Neural Optimal Transport with General Cost Functionals (3 citations)
- Accelerating Sinkhorn algorithm with sparse Newton iterations (1 citation)
- Energy-guided Entropic Neural Optimal Transport (1 citation)
- Generative Sliced MMD Flows with Riesz Kernels (1 citation)
- Sparsistency for inverse optimal transport (1 citation)
- LCOT: Linear Circular Optimal Transport
- Light Schrödinger Bridge
- SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
Submodular and game algorithms · 5 papers
- Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments (2 citations)
- Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions (1 citation)
- Generative Adversarial Equilibrium Solvers
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games
- Learning Nash Equilibria in Rank-1 Games