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
Differentiable Tree Operations Promote Compositional Generalization
Differentially Private Distributed Bayesian Linear Regression with MCMC
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
Differentially Private Hierarchical Clustering with Provable Approximation Guarantees
Differentially Private Optimization on Large Model at Small Cost
Differentially Private Sharpness-Aware Training
Differentially Private Stochastic Convex Optimization under a Quantile Loss Function
Differential Privacy has Bounded Impact on Fairness in Classification
Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
Diffusion Based Representation Learning
Diffusion Models are Minimax Optimal Distribution Estimators
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
Diffusion Models for Black-Box Optimization
Dimensionality Reduction for General KDE Mode Finding
Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing
Dink-Net: Neural Clustering on Large Graphs
Directed Chain Generative Adversarial Networks
Direct Parameterization of Lipschitz-Bounded Deep Networks
Dirichlet Diffusion Score Model for Biological Sequence Generation
DiscoBAX - Discovery of optimal intervention sets in genomic experiment design
DiscoBAX: Discovery of optimal intervention sets in genomic experiment design
Discover and Cure: Concept-aware Mitigation of Spurious Correlation
Discovering Object-Centric Generalized Value Functions From Pixels
Discover-Then-Rank Unlabeled Support Vectors in the Dual Space for Multi-Class Active Learning
Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models
Discrete Key-Value Bottleneck
Disentangled Generative Models for Robust Prediction of System Dynamics
Disentangled Multi-Fidelity Deep Bayesian Active Learning
Disentangled Multiplex Graph Representation Learning
Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
Distance Weighted Supervised Learning for Offline Interaction Data
Distilling Internet-Scale Vision-Language Models into Embodied Agents
Distortion and Uncertainty Aware Loss for Panoramic Depth Completion
Distributed Contextual Linear Bandits with Minimax Optimal Communication Cost
Distributed Linear Bandits under Communication Constraints
Distributional Offline Policy Evaluation with Predictive Error Guarantees
Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction
Distribution Free Domain Generalization
Distribution Free Prediction Sets for Node Classification
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
DIVISION: Memory Efficient Training via Dual Activation Precision
DoCoFL: Downlink Compression for Cross-Device Federated Learning
Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling
Does a Neural Network Really Encode Symbolic Concepts?
Does Continual Learning Equally Forget All Parameters?
Does Sparsity Help in Learning Misspecified Linear Bandits?
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule

« prev Page 9/38 next »