ICML 2023

1,862 papers

Top Research Directions

Research directions most represented by ICML 2023 papers.

Clean Accuracy Degradation in Machine Learning Defenses 32
The Non-Linear Function Approximation Gap in Reinforcement Learning 30
Overcoming the Iterative Inference Latency of Diffusion Models 23
Bypassing the Computational Bottleneck of Adversarial Training 23
Overcoming the Homophily Assumption in Graph Neural Networks 20
The Function Approximation Gap in Reinforcement Learning Theory 20
The Weisfeiler Lehman Expressivity Bottleneck 19
Over-Smoothing in Graph Neural Networks 19
Scaling Gaussian Processes Beyond Cubic Complexity 17
Scaling Reinforcement Learning to High-Dimensional Visual Observations 16
The Mechanics of Benign Overfitting in High Dimensions 15
Exploration Strategies for Sparse Reward Reinforcement Learning 15
Conformal Prediction for Rigorous Uncertainty Quantification 14
Overcoming the Cubic Complexity of Kernel Methods 14
The Mechanics of Backdoor Attacks in Neural Networks 14

Top Authors

AuthorPapers
Quanquan Gu14
Yoshua Bengio12
Bernhard Schölkopf11
Remi Munos11
Yunhao Tang10
Bo Han9
Michal Valko9
Pieter Abbeel9
Tongliang Liu9
Zhangyang Wang9
Jun Zhu8
Sergey Levine8
Stefano Ermon8
Junchi Yan7
Percy Liang7
Tianbao Yang7
Will Dabney7
Clare Lyle6
Dacheng Tao6
Kun Zhang6

Impactful Papers

Papers from ICML 2023 that shaped research clusters.

Foundational

Influential

Papers

Title
Learning-Rate-Free Learning by D-Adaptation
Learning Rate Schedules in the Presence of Distribution Shift
Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
Learning Representations without Compositional Assumptions
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
Learning Subpocket Prototypes for Generalizable Structure-based Drug Design
Learning Temporally AbstractWorld Models without Online Experimentation
Learning the Dynamics of Sparsely Observed Interacting Systems
Learning the Right Layers a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs
Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learning
Learning to Bid in Repeated First-Price Auctions with Budgets
Learning to Boost Training by Periodic Nowcasting Near Future Weights
Learning to Decouple Complex Systems
Learning to Design Analog Circuits to Meet Threshold Specifications
Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
Learning to Initiate and Reason in Event-Driven Cascading Processes
Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Learning to Maximize Mutual Information for Dynamic Feature Selection
Learning to Optimize Differentiable Games
Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator
Learning Unnormalized Statistical Models via Compositional Optimization
Learning useful representations for shifting tasks and distributions
Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
Learn to Accumulate Evidence from All Training Samples: Theory and Practice
LegendreTron: Uprising Proper Multiclass Loss Learning
Less is More: Task-aware Layer-wise Distillation for Language Model Compression
LESSON: Learning to Integrate Exploration Strategies for Reinforcement Learning via an Option Framework
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
Leveraging Demonstrations to Improve Online Learning: Quality Matters
Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks
Leveraging Offline Data in Online Reinforcement Learning
Leveraging Proxy of Training Data for Test-Time Adaptation
Leveraging VLM-Based Pipelines to Annotate 3D Objects
LEVER: Learning to Verify Language-to-Code Generation with Execution
Lifelong Language Pretraining with Distribution-Specialized Experts
Likelihood Adjusted Semidefinite Programs for Clustering Heterogeneous Data
Linear Causal Disentanglement via Interventions
Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies
Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach
Linear optimal partial transport embedding
Linear Time GPs for Inferring Latent Trajectories from Neural Spike Trains
Linkless Link Prediction via Relational Distillation
LinSATNet: The Positive Linear Satisfiability Neural Networks
LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control
Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
LIV: Language-Image Representations and Rewards for Robotic Control
Locally Regularized Neural Differential Equations: Some Black Boxes were meant to remain closed!
Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

« prev Page 19/38 next »