ICML 2024 accepted papers on Learning theory and algorithms
303 of the 2,610 papers accepted at ICML 2024 (11.6%) are on Learning theory and algorithms, compared with 15.2% at ICML 2023. They fall into 9 topics.
See ICML 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 · 82 papers
- Model Alignment as Prospect Theoretic Optimization (23 citations)
- The Linear Representation Hypothesis and the Geometry of Large Language Models (10 citations)
- Conformal Prediction Sets Improve Human Decision Making (8 citations)
- Conformal Prediction with Learned Features (2 citations)
- Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic Analysis (2 citations)
- Local vs. Global Interpretability: A Computational Complexity Perspective (2 citations)
- Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams (2 citations)
- Plug-in Performative Optimization (2 citations)
- Differentiable Distributionally Robust Optimization Layers (1 citation)
- Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees (1 citation)
- Generalized Preference Optimization: A Unified Approach to Offline Alignment (1 citation)
- KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions (1 citation)
and 70 more in the interactive map.
Sample complexity · 59 papers
- Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models (9 citations)
- Diffusion Posterior Sampling is Computationally Intractable (2 citations)
- Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping Compositions (2 citations)
- Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise (1 citation)
- Bottleneck-Minimal Indexing for Generative Document Retrieval (1 citation)
- Faster Maximum Inner Product Search in High Dimensions (1 citation)
- Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions (1 citation)
- On a Combinatorial Problem Arising in Machine Teaching (1 citation)
- Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages (1 citation)
- Sample Complexity Bounds for Estimating Probability Divergences under Invariances (1 citation)
- Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution (1 citation)
- Unmasking Vulnerabilities: Cardinality Sketches under Adaptive Inputs (1 citation)
and 47 more in the interactive map.
Kernels and regression theory · 43 papers
- A Statistical Theory of Regularization-Based Continual Learning (7 citations)
- Restoring balance: principled under/oversampling of data for optimal classification (5 citations)
- On Hypothesis Transfer Learning of Functional Linear Models (4 citations)
- Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss (3 citations)
- Optimal Ridge Regularization for Out-of-Distribution Prediction (2 citations)
- An Information-Theoretic Analysis of In-Context Learning (1 citation)
- Interpretability Illusions in the Generalization of Simplified Models (1 citation)
- Model Assessment and Selection under Temporal Distribution Shift (1 citation)
- Smoothness Adaptive Hypothesis Transfer Learning (1 citation)
- Statistical Properties of Robust Satisficing (1 citation)
- $H$-Consistency Guarantees for Regression
- A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples
and 31 more in the interactive map.
Combinatorial and search optimization · 36 papers
- Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification (10 citations)
- Graph2Tac: Online Representation Learning of Formal Math Concepts (4 citations)
- Smooth Tchebycheff Scalarization for Multi-Objective Optimization (3 citations)
- A fast algorithm to simulate nonlinear resistive networks (1 citation)
- A General Framework for Learning from Weak Supervision (1 citation)
- Adaptive Stabilization Based on Machine Learning for Column Generation (1 citation)
- Autonomous Sparse Mean-CVaR Portfolio Optimization (1 citation)
- Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation (1 citation)
- Trained Random Forests Completely Reveal your Dataset (1 citation)
- A New Branch-and-Bound Pruning Framework for $\ell_0$-Regularized Problems
- Amortizing Pragmatic Program Synthesis with Rankings
- Box Facets and Cut Facets of Lifted Multicut Polytopes
and 24 more in the interactive map.
Matrix and tensor methods · 26 papers
- Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models (3 citations)
- Inferring Change Points in High-Dimensional Linear Regression via Approximate Message Passing (1 citation)
- Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models (1 citation)
- Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation (1 citation)
- Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery
- Efficient Pareto Manifold Learning with Low-Rank Structure
- Fast Sampling-Based Sketches for Tensors
- Fast White-Box Adversarial Streaming Without a Random Oracle
- High-Dimensional Geometric Streaming for Nearly Low Rank Data
- Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting
- Non-parametric Online Change Point Detection on Riemannian Manifolds
- On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis
and 14 more in the interactive map.
Fairness · 16 papers
- Position: Amazing Things Come From Having Many Good Models (6 citations)
- Fair Resource Allocation in Multi-Task Learning (4 citations)
- On The Fairness Impacts of Hardware Selection in Machine Learning (2 citations)
- Fair Off-Policy Learning from Observational Data (1 citation)
- Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks (1 citation)
- FairProof : Confidential and Certifiable Fairness for Neural Networks (1 citation)
- Centralized Selection with Preferences in the Presence of Biases
- Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
- FRAPPÉ: A Group Fairness Framework for Post-Processing Everything
- How Far Can Fairness Constraints Help Recover From Biased Data?
- On the Maximal Local Disparity of Fairness-Aware Classifiers
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making
and 4 more in the interactive map.
Submodular and game algorithms · 15 papers
- A Persuasive Approach to Combating Misinformation (3 citations)
- A Field Guide for Pacing Budget and ROS Constraints (2 citations)
- Equilibrium of Data Markets with Externality (1 citation)
- Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach (1 citation)
- A Dynamic Algorithm for Weighted Submodular Cover Problem
- A Geometric Decomposition of Finite Games: Convergence vs. Recurrence under Exponential Weights
- Bootstrapping Fisher Market Equilibrium and First-Price Pacing Equilibrium
- Can a Few Decide for Many? The Metric Distortion of Sortition
- Chasing Convex Functions with Long-term Constraints
- Graphon Mean Field Games with a Representative Player: Analysis and Learning Algorithm
- Optimally Improving Cooperative Learning in a Social Setting
- Roping in Uncertainty: Robustness and Regularization in Markov Games
and 3 more in the interactive map.
Clustering · 15 papers
- Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better (2 citations)
- Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond (1 citation)
- MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations (1 citation)
- A Near-Linear Time Approximation Algorithm for Beyond-Worst-Case Graph Clustering
- Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering
- Dynamic Correlation Clustering in Sublinear Update Time
- Dynamic Spectral Clustering with Provable Approximation Guarantee
- Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large Graphs
- New Bounds on the Cohesion of Complete-link and Other Linkage Methods for Agglomerative Clustering
- Analyzing $D^\alpha$ seeding for $k$-means
- EDISON: Enhanced Dictionary-Induced Tensorized Incomplete Multi-View Clustering with Gaussian Error Rank Minimization
- Multi-View Clustering by Inter-cluster Connectivity Guided Reward
and 3 more in the interactive map.
Optimal transport · 11 papers
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (3 citations)
- Estimating Barycenters of Distributions with Neural Optimal Transport
- Generalized Sobolev Transport for Probability Measures on a Graph
- Generative Conditional Distributions by Neural (Entropic) Optimal Transport
- Light and Optimal Schrödinger Bridge Matching
- Neural Networks Learn Statistics of Increasing Complexity
- Quantum Theory and Application of Contextual Optimal Transport
- Stereographic Spherical Sliced Wasserstein Distances
- Submodular framework for structured-sparse optimal transport
- Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformer
- Stability Evaluation through Distributional Perturbation Analysis