ICLR 2022

2,337 papers

Top Research Directions

Research directions most represented by ICLR 2022 papers.

Bypassing the Computational Bottleneck of Adversarial Training 21
Sample Efficient Reinforcement Learning 19
The Mechanics of Benign Overfitting in High Dimensions 18
Clean Accuracy Degradation in Machine Learning Defenses 17
Overcoming the Homophily Assumption in Graph Neural Networks 13
Accelerating Sparse Neural Networks on Dense Hardware 13
Accelerating Neural Architecture Search Without Full Model Training 12
The Non-Linear Function Approximation Gap in Reinforcement Learning 12
The Mechanics of Backdoor Attacks in Neural Networks 12
Beyond the Lazy Training Regime of Neural Networks 11
The Infinite Width Approximation Gap in Deep Learning 10
Matrix-Free Curvature Estimation for Deep Learning 10
The Computational Overhead of Iterative Model Pruning 9
The Weisfeiler Lehman Expressivity Bottleneck 9
Why Theoretical FLOPs Fail to Predict Real Latency 9

Top Authors

AuthorPapers
Zhangyang Wang23
Sergey Levine21
Tianlong Chen15
Tongliang Liu14
Bo Han13
Chelsea Finn13
Gang Niu13
Jun Wang13
Yoshua Bengio13
Bernhard Schölkopf12
Joshua B. Tenenbaum12
J Zico Kolter12
Ping Li12
Tie-Yan Liu12
Dacheng Tao11
Stephan Günnemann11
Tom Goldstein11
Masashi Sugiyama10
Pieter Abbeel9
Pin-Yu Chen9

Impactful Papers

Papers from ICLR 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
How Low Can We Go: Trading Memory for Error in Low-Precision Training
How many degrees of freedom do we need to train deep networks: a loss landscape perspective
How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem
How Much Can CLIP Benefit Vision-and-Language Tasks?
How to Adapt Your Large-Scale Vision-and-Language Model
How to deal with missing data in supervised deep learning?
How to Improve Sample Complexity of SGD over Highly Dependent Data?
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data
How to measure deep uncertainty estimation performance and which models are naturally better at providing it
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
How to train RNNs on chaotic data?
How to Train Your MAML to Excel in Few-Shot Classification
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis
How Well Does Self-Supervised Pre-Training Perform with Streaming Data?
HTLM: Hyper-Text Pre-Training and Prompting of Language Models
Huber Additive Models for Non-stationary Time Series Analysis
Human-AI Coordination via Human-Regularized Search and Learning
Human-Level Control without Server-Grade Hardware
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation
Hybrid Cloud-Edge Networks for Efficient Inference
Hybrid Local SGD for Federated Learning with Heterogeneous Communications
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
Hybrid Random Features
HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models
HyperCGAN: Text-to-Image Synthesis with HyperNet-Modulated Conditional Generative Adversarial Networks
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning
Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs
Hyperparameter Tuning with Renyi Differential Privacy
HyperTransformer: Attention-Based CNN Model Generation from Few Samples
Hypothesis Driven Coordinate Ascent for Reinforcement Learning
IA-MARL: Imputation Assisted Multi-Agent Reinforcement Learning for Missing Training Data
Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning
iFlood: A Stable and Effective Regularizer
IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes
If your data distribution shifts, use self-learning
Igeood: An Information Geometry Approach to Out-of-Distribution Detection
IGLU: Efficient GCN Training via Lazy Updates
Illiterate DALL-E Learns to Compose
iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
Image BERT Pre-training with Online Tokenizer
Image Compression and Classification Using Qubits and Quantum Deep Learning
Image Functions In Neural Networks: A Perspective On Generalization
Imbalanced Adversarial Training with Reweighting
Imbedding Deep Neural Networks
Imitation Learning by Reinforcement Learning
Imitation Learning from Observations under Transition Model Disparity
Imitation Learning from Pixel Observations for Continuous Control

« prev Page 20/47 next »