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
PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient
Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute
Predictable MDP Abstraction for Unsupervised Model-Based RL
Predicting Ordinary Differential Equations with Transformers
Predicting Rare Events by Shrinking Towards Proportional Odds
Predictive Flows for Faster Ford-Fulkerson
Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search
Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems
Pre-training for Speech Translation: CTC Meets Optimal Transport
Pretraining Language Models with Human Preferences
Pricing Experimental Design: Causal Effect, Expected Revenue and Tail Risk
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
Principled Acceleration of Iterative Numerical Methods Using Machine Learning
Principled Offline RL in the Presence of Rich Exogenous Information
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
Private Federated Learning with Autotuned Compression
Private Statistical Estimation of Many Quantiles
Probabilistic Attention-to-Influence Neural Models for Event Sequences
Probabilistic Categorical Adversarial Attack and Adversarial Training
Probabilistic Concept Bottleneck Models
Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputs
Probabilistic Imputation for Time-series Classification with Missing Data
Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models
Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
Progressive Purification for Instance-Dependent Partial Label Learning
Projected Tensor Power Method for Hypergraph Community Recovery
Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
Prompting Large Language Model for Machine Translation: A Case Study
Propensity Matters: Measuring and Enhancing Balancing for Recommendation
Proper Losses for Discrete Generative Models
Proper Scoring Rules for Survival Analysis
Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an Experimentalist
Protecting Language Generation Models via Invisible Watermarking
Prototype-oriented unsupervised anomaly detection for multivariate time series
Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
Provable Benefit of Mixup for Finding Optimal Decision Boundaries
Provable Data Subset Selection For Efficient Neural Networks Training
Provable Dynamic Fusion for Low-Quality Multimodal Data
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
Provable Reset-free Reinforcement Learning by No-Regret Reduction
Provably and Practically Efficient Neural Contextual Bandits
Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP
Provably Invariant Learning without Domain Information

« prev Page 27/38 next »