---
title: "ICML 2020 — accepted papers — Elamur Research"
description: "ICML 2020 — accepted papers: 1 paper in the Elamur Research library, with our summaries, ranked by citations."
canonical: "https://research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2020/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2020/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [ICML](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/) / 2020

# ICML 2020 — accepted papers

ICML 2020 is the 2020 edition of the International Conference on Machine Learning (ICML). OpenAlex lists 189 papers of it; our library holds 1 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

[**189** papers in the proceedings](#all) · [**1** work in our library](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2020/#works) · [**153** citations of these works](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2020/#works)

## Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. **[Generative Pretraining From Pixels ↗](http://proceedings.mlr.press/v119/chen20s/chen20s.pdf)**Mark I-Cheng Chen, Alec Radford, Rewon Child et al.*512 citations*
2. **[PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization ↗](http://proceedings.mlr.press/v119/zhang20ae/zhang20ae.pdf)**Jingqing Zhang, Yao Zhao, Mohammad Saleh et al.*325 citations*
3. **[XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation ↗](http://proceedings.mlr.press/v119/hu20b/hu20b.pdf)**Junjie Hu, Sebastian Ruder, Aditya Siddhant et al.*297 citations*
4. **[Retrieval Augmented Language Model Pre-Training ↗](http://proceedings.mlr.press/v119/guu20a/guu20a.pdf)**Kelvin Guu, Kenton Lee, Zora Tung et al.*199 citations*
5. **[Data-Efficient Image Recognition with Contrastive Predictive Coding ↗](http://proceedings.mlr.press/v119/henaff20a/henaff20a.pdf)**Olivier J. Hénaff*154 citations*
6. **[NGBoost: Natural Gradient Boosting for Probabilistic Prediction ↗](http://proceedings.mlr.press/v119/duan20a/duan20a.pdf)**Tony Duan, Anand Avati, Daisy Yi Ding et al.*108 citations*
7. **[Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ↗](http://proceedings.mlr.press/v119/li20m/li20m.pdf)**Zhuohan Li, Eric Wallace, Sheng Shen et al.*97 citations*
8. **[Rigging the Lottery: Making All Tickets Winners ↗](http://proceedings.mlr.press/v119/evci20a/evci20a.pdf)**Utku Evci, Trevor Gale, Jacob Menick et al.*90 citations*
9. **[An Optimistic Perspective on Offline Deep Reinforcement Learning ↗](http://proceedings.mlr.press/v119/agarwal20c/agarwal20c.pdf)**Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi*79 citations*
10. **[Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data ↗](http://proceedings.mlr.press/v119/guo20i/guo20i.pdf)**Lan-Zhe Guo, Zhenyu Zhang, Yuan Ying Jiang et al.*77 citations*

## All accepted papers (189)

The most cited first; 1 with our summary link to their page here, the others to the original.

1. **[Generative Pretraining From Pixels ↗](http://proceedings.mlr.press/v119/chen20s/chen20s.pdf)**Mark I-Cheng Chen, Alec Radford, Rewon Child et al.*512 citations*
2. **[PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization ↗](http://proceedings.mlr.press/v119/zhang20ae/zhang20ae.pdf)**Jingqing Zhang, Yao Zhao, Mohammad Saleh et al.*325 citations*
3. **[XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation ↗](http://proceedings.mlr.press/v119/hu20b/hu20b.pdf)**Junjie Hu, Sebastian Ruder, Aditya Siddhant et al.*297 citations*
4. **[Retrieval Augmented Language Model Pre-Training ↗](http://proceedings.mlr.press/v119/guu20a/guu20a.pdf)**Kelvin Guu, Kenton Lee, Zora Tung et al.*199 citations*
5. **[Data-Efficient Image Recognition with Contrastive Predictive Coding ↗](http://proceedings.mlr.press/v119/henaff20a/henaff20a.pdf)**Olivier J. Hénaff*154 citations*
6. **[NGBoost: Natural Gradient Boosting for Probabilistic Prediction ↗](http://proceedings.mlr.press/v119/duan20a/duan20a.pdf)**Tony Duan, Anand Avati, Daisy Yi Ding et al.*108 citations*
7. **[Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ↗](http://proceedings.mlr.press/v119/li20m/li20m.pdf)**Zhuohan Li, Eric Wallace, Sheng Shen et al.*97 citations*
8. **[Rigging the Lottery: Making All Tickets Winners ↗](http://proceedings.mlr.press/v119/evci20a/evci20a.pdf)**Utku Evci, Trevor Gale, Jacob Menick et al.*90 citations*
9. **[An Optimistic Perspective on Offline Deep Reinforcement Learning ↗](http://proceedings.mlr.press/v119/agarwal20c/agarwal20c.pdf)**Rishabh Agarwal, Dale Schuurmans, Mohammad Norouzi*79 citations*
10. **[Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data ↗](http://proceedings.mlr.press/v119/guo20i/guo20i.pdf)**Lan-Zhe Guo, Zhenyu Zhang, Yuan Ying Jiang et al.*77 citations*
11. **[What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? ↗](http://proceedings.mlr.press/v119/jin20e/jin20e.pdf)**Chi Jin, Praneeth Netrapalli, Michael I. Jordan*66 citations*
12. **[Detecting Out-of-Distribution Examples with Gram Matrices ↗](http://proceedings.mlr.press/v119/sastry20a/sastry20a.pdf)**Chandramouli Shama Sastry, Sageev Oore*65 citations*
13. **[Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack ↗](http://proceedings.mlr.press/v119/croce20a/croce20a.pdf)**Francesco Croce, Matthias Hein*63 citations*
14. **[Accelerating Large-Scale Inference with Anisotropic Vector Quantization ↗](http://proceedings.mlr.press/v119/guo20h/guo20h.pdf)**Ruiqi Guo, Quan Geng, David Simcha et al.*62 citations*
15. **[Learning to Simulate Complex Physics with Graph Networks ↗](http://proceedings.mlr.press/v119/sanchez-gonzalez20a/sanchez-gonzalez20a.pdf)**Álvaro Palomo Sánchez, Jonathan Godwin, Tobias Pfaff et al.*61 citations*
16. **[Learning with Good Feature Representations in Bandits and in RL with a Generative Model ↗](http://proceedings.mlr.press/v119/lattimore20a/lattimore20a.pdf)**Gellért Weisz, Tor Lattimore, Csaba Szepesvári*48 citations*
17. **[Stabilizing Transformers for Reinforcement Learning ↗](http://proceedings.mlr.press/v119/parisotto20a/parisotto20a.pdf)**Emilio Parisotto, Francis Song, Jack W. Rae et al.*46 citations*
18. **[From Local SGD to Local Fixed Point Methods for Federated Learning ↗](http://proceedings.mlr.press/v119/malinovskiy20a/malinovskiy20a.pdf)**Grigory Malinovsky, Dmitry A. Kovalev, Elnur Gasanov et al.*45 citations*
19. **[Improving Transformer Optimization Through Better Initialization ↗](http://proceedings.mlr.press/v119/huang20f/huang20f.pdf)**Xiao Shi Huang, Juan Manuel Pérez, Jimmy Lei Ba et al.*45 citations*
20. **[Leveraging Procedural Generation to Benchmark Reinforcement Learning ↗](http://proceedings.mlr.press/v119/cobbe20a/cobbe20a.pdf)**Karl Cobbe, Chris Hesse, Jacob Hilton et al.*40 citations*
21. **[Implicit Learning Dynamics in Stackelberg Games: Equilibria Characterization, Convergence Analysis, and Empirical Study ↗](http://proceedings.mlr.press/v119/fiez20a/fiez20a.pdf)**Tanner Fiez, Benjamin J. Chasnov, Lillian J. Ratliff*38 citations*
22. **[Multi-Task Learning with User Preferences: Gradient Descent with Controlled Ascent in Pareto Optimization ↗](http://proceedings.mlr.press/v119/mahapatra20a/mahapatra20a.pdf)**Debabrata Mahapatra, Vaibhav Rajan*34 citations*
23. **[Strategic Classification is Causal Modeling in Disguise ↗](http://proceedings.mlr.press/v119/miller20b/miller20b.pdf)**John Arthur Miller, Smitha Milli*32 citations*
24. **[Concise Explanations of Neural Networks using Adversarial Training ↗](http://proceedings.mlr.press/v119/chalasani20a/chalasani20a.pdf)**Prasad Chalasani, Jiefeng Chen, Amrita Roy Chowdhury et al.*29 citations*
25. **[Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking ↗](http://proceedings.mlr.press/v119/sun20a/sun20a.pdf)**Haoran Sun, Songtao Lu, Mingyi Hong*29 citations*

[See all 189 papers in ICML 2020 — accepted papers →](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2020/papers/)

## Papers with our summary in our library (1)

The most cited first (OpenAlex citations plus our library's).

1. **[Memory-Efficient Pipeline-Parallel DNN Training](https://md.research.elamur.ai/free/en/papers/narayanan-2020-memory-efficient-pipeline-parallel-dnn/) [International Conference on Machine Learning (ICML)](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/)**Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, et al.*2020 · 153 citations*

## Top topics

Topics of its works in our library, with the number of works on each.

[Efficient models & compression (1)](https://md.research.elamur.ai/free/en/topics/efficient-models/)

## Fields

[Computer Science (1)](https://md.research.elamur.ai/free/en/shelves/computer-science/)

## Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

[🧑‍🔬**Amar Phanishayee**1 work here · 153 citations](https://md.research.elamur.ai/free/en/authors/amar-phanishayee/) · [🧑‍🔬**Deepak Narayanan**1 work here · 153 citations](https://md.research.elamur.ai/free/en/authors/deepak-narayanan/) · [🧑‍🔬**Matei Zaharia**1 work here · 153 citations](https://md.research.elamur.ai/free/en/authors/matei-zaharia/) · [🧑‍🔬**Xie Chen**1 work here · 153 citations](https://md.research.elamur.ai/free/en/authors/xie-chen/)

## Top institutions

Institutions on the bylines of its works here, by the number of works.

[🏢**Microsoft** Redmond · United States 1 work here](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🏢**Databricks** San Francisco · United States 1 work here](https://md.research.elamur.ai/free/en/companies/databricks/) · [🎓**Stanford University** Stanford · United States 1 work here](https://md.research.elamur.ai/free/en/universities/stanford-university/)

works and citations from OpenAlex and our library.

- [← previous ICML 2019](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2019/)
- [next → ICML 2021](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2021/)
- [↑ back to ICML](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/)