ICLR 2019 accepted papers by research area
502 papers were accepted at ICLR 2019 (+165 vs 2018). Here is how they split across 20 research areas, and which topics gained the most ground.
See ICLR 2019 in the interactive map
Submitting to ICLR? Checklist →
Research areas
| Area | Papers | Share | Change in share vs 2018 |
|---|---|---|---|
| Architectures and efficiency | 83 | 16.5% | -7.5 pts |
| Reinforcement learning | 63 | 12.5% | +1.9 pts |
| Probabilistic and scientific modeling | 61 | 12.2% | +2.1 pts |
| Label-efficient and robust learning | 56 | 11.2% | +0.2 pts |
| Optimization | 43 | 8.6% | +1.1 pts |
| Image generation | 38 | 7.6% | -0.1 pts |
| Learning theory and algorithms | 37 | 7.4% | +0.2 pts |
| Adversarial robustness and security | 29 | 5.8% | -0.5 pts |
| Graph learning | 18 | 3.6% | +1.2 pts |
| Multi-agent systems and games | 15 | 3.0% | -1.8 pts |
| Large language models | 11 | 2.2% | +0.7 pts |
| Detection and segmentation | 11 | 2.2% | +1.3 pts |
| Vision-language and multimodal | 8 | 1.6% | +0.1 pts |
| 3D vision | 7 | 1.4% | +1.4 pts |
| Continual learning | 6 | 1.2% | -0.6 pts |
| Video | 6 | 1.2% | steady |
| Time series | 4 | 0.8% | +0.5 pts |
| Bandits and online learning | 2 | 0.4% | -0.2 pts |
| Federated learning and privacy | 2 | 0.4% | -0.5 pts |
| Point clouds | 2 | 0.4% | +0.4 pts |
Fastest-growing topics at ICLR 2019
Change in share of ICLR papers from 2018 to 2019, topics with at least 10 papers.
- Visual and representation RL (Reinforcement learning): 16 → 41 papers
- Prediction and decision losses (Learning theory and algorithms): 4 → 12 papers
- Uncertainty and Gaussian processes (Probabilistic and scientific modeling): 3 → 10 papers
- Variational and generative sampling (Probabilistic and scientific modeling): 18 → 31 papers
- Certified and empirical robustness (Adversarial robustness and security): 12 → 22 papers
- Molecules and proteins (Probabilistic and scientific modeling): 6 → 13 papers
- Implicit bias and generalization (Optimization): 9 → 16 papers
- Domain adaptation and generalization (Label-efficient and robust learning): 6 → 11 papers
- Recognition and long-tail (Label-efficient and robust learning): 22 → 34 papers
- Optimizers (Optimization): 13 → 15 papers
More venues
Same year: ICML 2019 · NeurIPS 2019 · CVPR 2019 · AAAI 2019 · ICCV 2019 · TPAMI 2019 · IJCV 2019 · JMLR 2019
ICLR in other years: 2017 · 2018 · 2020 · 2021 · 2022 · 2023 · 2024 · 2025 · 2026
