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
KDEformer: Accelerating Transformers via Kernel Density Estimation
Kernel Logistic Regression Approximation of an Understandable ReLU Neural Network
Kernel QuantTree
Kernel Sufficient Dimension Reduction and Variable Selection for Compositional Data via Amalgamation
K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs
Label differential privacy and private training data release
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Language Instructed Reinforcement Learning for Human-AI Coordination
Large Language Models Can Be Easily Distracted by Irrelevant Context
Large Language Models Struggle to Learn Long-Tail Knowledge
Last Switch Dependent Bandits with Monotone Payoff Functions
Latent Traversals in Generative Models as Potential Flows
Layered State Discovery for Incremental Autonomous Exploration
Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning
LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation
LeadFL: Client Self-Defense against Model Poisoning in Federated Learning
Learnability and Algorithm for Continual Learning
Learning Affinity with Hyperbolic Representation for Spatial Propagation
Learning Antidote Data to Individual Unfairness
Learning-augmented private algorithms for multiple quantile release
Learning Belief Representations for Partially Observable Deep RL
Learning Compiler Pass Orders using Coreset and Normalized Value Prediction
Learning Control by Iterative Inversion
Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows
Learning Control-Oriented Dynamical Structure from Data
Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic
Learning Deep Time-index Models for Time Series Forecasting
Learning Dense Correspondences between Photos and Sketches
Learning Distributions over Quantum Measurement Outcomes
Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
Learning Functional Distributions with Private Labels
Learning GFlowNets From Partial Episodes For Improved Convergence And Stability
Learning Globally Smooth Functions on Manifolds
Learning Hidden Markov Models When the Locations of Missing Observations are Unknown
Learning in POMDPs is Sample-Efficient with Hindsight Observability
Learning Instance-Specific Augmentations by Capturing Local Invariances
Learning Intuitive Policies Using Action Features
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
Learning Mixtures of Gaussians with Censored Data
Learning Mixtures of Markov Chains and MDPs
Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics
Learning Neural PDE Solvers with Parameter-Guided Channel Attention
Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation
Learning Perturbations to Explain Time Series Predictions
Learning Physical Models that Can Respect Conservation Laws
Learning Preconditioners for Conjugate Gradient PDE Solvers
Learning Prescriptive ReLU Networks

« prev Page 18/38 next »