ICML 2022

1,154 papers

Top Research Directions

Research directions most represented by ICML 2022 papers.

The Non-Linear Function Approximation Gap in Reinforcement Learning 23
Clean Accuracy Degradation in Machine Learning Defenses 22
Scaling Gaussian Processes Beyond Cubic Complexity 17
Provably Efficient Reinforcement Learning with Linear MDPs 15
The Function Approximation Gap in Reinforcement Learning Theory 15
Bypassing the Computational Bottleneck of Adversarial Training 14
Loss Landscape Flatness and the Generalization Gap 13
Mitigating Gradient Variance in Policy Optimization 13
Distribution Shift in Offline Reinforcement Learning 12
Scaling Bandit Learning to Large Action Spaces 10
Multi-Agent Learning Under Bandit Feedback 10
Horizon Free Bounds in Reinforcement Learning 10
Periodic Synchronization for Communication Efficient Distributed Learning 10
Optimistic Exploration for Efficient Reinforcement Learning 10
Matrix-Free Curvature Estimation for Deep Learning 10

Top Authors

AuthorPapers
Zhangyang Wang9
Zhaoran Wang9
Zhuoran Yang9
Bo Li7
Jun Zhu7
Shandian Zhe7
Tianbao Yang7
Bernhard Schölkopf6
Bo Han6
Manzil Zaheer6
Mihaela van der Schaar6
Nhat Ho6
Pranjal Awasthi6
Sergey Levine6
Tianlong Chen6
Yang Liu6
Andreas Krause5
David Woodruff5
Michael W. Mahoney5
Peter Richtárik5

Impactful Papers

Papers from ICML 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization
Neural Tangent Kernel Empowered Federated Learning
Neurocoder: General-Purpose Computation Using Stored Neural Programs
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
Neuron Dependency Graphs: A Causal Abstraction of Neural Networks
Neuro-Symbolic Hierarchical Rule Induction
Neurotoxin: Durable Backdoors in Federated Learning
NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks
NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
NOMU: Neural Optimization-based Model Uncertainty
(Non-)Convergence Results for Predictive Coding Networks
Nonlinear Feature Diffusion on Hypergraphs
Nonparametric Embeddings of Sparse High-Order Interaction Events
Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition
Nonparametric Involutive Markov Chain Monte Carlo
Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes
Non-Vacuous Generalisation Bounds for Shallow Neural Networks
No-Regret Learning in Partially-Informed Auctions
No-Regret Learning in Time-Varying Zero-Sum Games
Not All Poisons are Created Equal: Robust Training against Data Poisoning
N-Penetrate: Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations
NP-Match: When Neural Processes meet Semi-Supervised Learning
NysADMM: faster composite convex optimization via low-rank approximation
Nyström Kernel Mean Embeddings
Object Permanence Emerges in a Random Walk along Memory
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Offline RL Policies Should Be Trained to be Adaptive
Off-Policy Evaluation for Large Action Spaces via Embeddings
Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory
Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
On Collective Robustness of Bagging Against Data Poisoning
On Convergence of Gradient Descent Ascent: A Tight Local Analysis
On Distribution Shift in Learning-based Bug Detectors
One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes
One-Pass Diversified Sampling with Application to Terabyte-Scale Genomic Sequence Streams
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
On Implicit Bias in Overparameterized Bilevel Optimization
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning
On Last-Iterate Convergence Beyond Zero-Sum Games
On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Online Active Regression
Online Algorithms with Multiple Predictions
Online and Consistent Correlation Clustering
Online Balanced Experimental Design
Online Continual Learning through Mutual Information Maximization
Online Decision Transformer
Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards
Online Learning for Min Sum Set Cover and Pandora's Box

« prev Page 15/24 next »