Pre-registration in a nutshell

Separate the generation and confirmation of hypotheses:

   Come up with an exciting research question   

   Write a paper proposal without confirmatory experiments   

   After the paper is accepted, run the experiments and report your results   

What does science get?

  • A healthy mix of positive and negative results
  • Reasonable ideas that don’t work still get published, avoiding wasteful replications
  • Papers are evaluated on the basis of scientific interest, not whether they achieve the best results

What do you get?

  • It's easier to plan your research: get feedback before investing in lengthy experiments
  • Your research is stronger: results have increased credibility
  • Convince people that they will learn something even if the result is negative


Sarahanne Field

University of Groningen
Preregistration: Introduction and Application to ML

Dima Damen

University of Bristol
Defending the Undefendable - Why I support peer reviewing?

Hugo Larochelle

Google & University of Montreal
Transactions on Machine Learning Research: A New Open Journal for Machine Learning

Paul Smaldino

UC Merced
Preregistration: A Reasonably Good Idea In A Time of Crisis

Schedule (December 13)

Time (UTC)SessionDuration
12:00Opening Remarks0:10
12:10Sarahanne Field (Invited Talk)
Preregistration: Introduction and Application to ML
12:40Oral Session 1
PCA Retargeting: Encoding Linear Shape Models as Convolutional Mesh Autoencoders (Eimear O'Sullivan)
13:00Spotlights 1 (5 x 3 min)0:20
13:20Oral Session 2
Unsupervised Resource Allocation with Graph Neural Networks (Miles Cranmer)
14:10Dima Damen (Invited Talk)
Defending the Undefendable - Why I support peer reviewing?
14:40Hugo Larochelle (Invited Talk)
Transactions on Machine Learning Research: A New Open Journal for Machine Learning
15:10Spotlights 2 (5 x 3 min)0:20
15:30 Poster Session 1:00
17:00Paul Smaldino (Invited Talk)
Preregistration: A Reasonably Good Idea In A Time of Crisis
17:30Oral Session 3
Confronting Domain Shift in Trained Neural Networks (Carianne Martinez)
17:502020 Authors' Experience (Discussion Panel)0:15
18:05Open Discussion1:00
19:05Closing Remarks0:05

Accepted proposals

Including a playlist of all 3-minute spotlight videos.

ID Authors Title Proposal Video Poster
3 Shubhaankar Gupta, Thomas P. O’Connell, Bernhard Egger Beyond Flatland: Pre-training with a Strong 3D Inductive Bias Proposal Video Poster
6 Mikolaj Czerkawski, Javier Cardona, Robert Atkinson, Craig Michie, Ivan Andonovic, Carmine Clemente, Christos Tachtatzis Neural Weight Step Video Compression Proposal Video Poster
8 Hamid Eghbal-zadeh, Gerhard Widmer How Much is an Augmented Sample Worth? Proposal Video Poster
10 Steven Lang, Martin Mundt, Fabrizio Ventola, Robert Peharz, Kristian Kersting Elevating Perceptual Sample Quality in Probabilistic Circuits through Differentiable Sampling Proposal Video Poster
11 Rohit Lal, Arihant Gaur, Aadhithya Iyer, Muhammed Abdullah Shaikh, Ritik Agrawal, Shital Chiddarwar Open-Set Multi-Source Multi-Target Domain Adaptation Proposal Supmat Video Poster
15 Sebastian Palacio, Federico Raue, Tushar Karayil, Jörn Hees, Andreas Dengel IteROAR: Quantifying the Interpretation of Feature Importance Methods Proposal Video Poster
18 Kshitij Ambilduke, Aneesh Shetye, Diksha Bagade, Rishika Bhagwatkar, Khurshed Fitter, Prasad Vagdargi, Shital Chiddarwar Enhancing Context Through Contrast Proposal Video Poster
19 Shuyang Li, Huanru Henry Mao, Julian McAuley Variable Bitrate Discrete Neural Representations via Causal Self-Attention Proposal Video Poster
26 Pierre Thodoroff, Wenyu Li, Neil D. Lawrence Benchmarking Real-Time Reinforcement Learning Proposal Video Poster
29 Vaasudev Narayanan, Aniket Anand Deshmukh, Urun Dogan, Vineeth N Balasubramaniam On Challenges in Unsupervised Domain Generalization Proposal Video Poster

Preregistration in more detail

What is pre-registration and how does it improve peer-review? Benchmarks on popular datasets have played a key role in the considerable measurable progress that machine learning has made in the last few years. But reviewers can be tempted to prioritise incremental improvements in benchmarks to the detriment of other scientific criteria, destroying many good ideas in their infancy. Authors can also feel obligated to make orthogonal improvements in order to “beat the state-of-the-art”, making the main contribution hard to assess.

Pre-registration changes the incentives by reviewing and accepting a paper before experiments are conducted. The emphasis of peer-review will be on whether the experiment plan can adequately prove or disprove one (or more) hypotheses. Some results will be negative, and this is welcomed. This way, good ideas that do not work will get published, instead of filed away and wastefully replicated many times by different groups. Finally, the clear separation between hypothesizing and confirmation (absent in the current review model) will raise the statistical significance of the results.

Call for Papers: We are inviting submissions on the range of topics covered at NeurIPS! Pre-registered papers will be published at the workshop, which is non-archival. After NeurIPS, authors will have the opportunity to submit the results paper to the Proceedings of Machine Learning Research (PMLR), a sister publication to the Journal of Machine Learning Research (JMLR). (you can find last year's proceedings here). The review process for this second stage will aim to ensure that the authors have performed a good-faith attempt to complete the experiments described in their proposal paper.

Paper submission process

→ There are two phases. The first one involves the presentation of paper proposals and will conclude with NeurIPS 2021 workshop day. The experiment phase will start after the acceptance of the proposals and will continue after the day of the workshop.
→ The deadline for the proposal is September the 19th. The deadline for the results is 30th April, 7th May 2022 (23:59 AoE timezone). Link to CMT.
→ The proposal is non-archival and will be included in the workshop proceedings. The full papers, formed as the collation of proposal and results, will each published as a journal in a PMLR volume.
→ Please read our tutorial before submitting, which you can find here. The paper structure and general rationale is different to what you may be used to. Even if the proposals must not include experimental results, it is important to carefully design and describe the experimental protocol, with the aim of eventually obtaining conclusive results.
→ You can submit here via CMT. For your proposals, please use our modified NeurIPS template.
→ For the proposal, the maximum length is five pages (references excluded). For the full papers there is not a strict limit, although we recommend to limit the experiments to a maximum extra four pages with respect to the proposal.
→ For inspiration, have a look at the other sections of this website, which provide further information. Moreover, you can find all the videos and proposals of last year edition here, and the PMLR volume with the full papers from 2020 workshop here.

Paper submission dates

1) Proposal phase:

Selection of pre-registered papers for the NeurIPS Workshop

 19th Sept 2021  Paper submission (authors)
 20th Sept to 27th Sept 2021  Review period (reviewers)
 1st Oct to 8th Oct 2021  Rebuttal period (authors)
 22nd Oct 2021  Notification of decisions
 1st Dec 2021  Camera ready submission (authors)
 13th Dec 2021  NeurIPS 2021 workshop day

2) Results phase:

Selection of results papers for PMLR journal

30th April, 7th May 2022 (23:59 AoE timezone). Link to CMT  Full paper (with results) submission (authors)


Samuel Albanie
Samuel Albanie
University of Cambridge
João F. Henriques
João F. Henriques
University of Oxford
Alex Hernandez-García
Alex Hernández-García
Mila (Quebec AI Institute) and Université de Montréal
Hazel Doughty
Hazel Doughty
University of Amsterdam
Gül Varol
Gül Varol
École des Ponts ParisTech


Many thanks to all the reviewers for their help!

Adrian Javaloy
Adrian Spurr
Alex Hernandez Garcia
Andrew Gambardella
Arnout Devos
Ayush Jaiswal
Bernardino Romera-Paredes
Brad J Gram-Hansen
Carianne Martinez
Cees Snoek
Chaitanya Devaguptapu
Chaoning Zhang
Chen Sun
David Krueger
Dimitris Tsipras
Disha Shrivastava
Efstratios Gavves
Emir Konuk
Emmanuel Bengio
Erika Lu
Evangelos Kazakos
Francesco Ferroni
Francesco Pinto
Francisco Girbal Eiras
Hadrien Bertrand
Hamid Eghbal-zadeh
Harkirat Behl
Jack Valmadre
James Thornton
Jason S. Hartford
Joseph Viviano
Konstantinos Tertikas
Lénaïc Chizat
Li Shen
Liliane Momeni
Malik H. Altakrori
Martin Mundt
Mélisande Teng
Michele Svanera
Miguel-Ángel Fernández-Torres
Nazanin M. Sepahvand
Oriane Siméoni
Paul Rubenstein
Rishabh Agarwal
Robert M. Gower
Romain Mueller
Ruizhe Li
Sadegh Aliakbarian
Safa Alver
Shahab Bakhtiari
Shangzhe Wu
Sharath Chandra Raparthy
Steffen Schneider
Steinar Laenen
Taoli Cheng
Tom Joy
Udo M. Schlegel
Victor Schmidt
Vincent Dumoulin
Vincent Mai
Viveka Kulharia
Xavier Gibert
Xutan Peng
Yana Hasson
Yongtuo Liu
Yuge Shi
Yuki M. Asano
Yunhua Zhang
Zhao Yang
Zhongdao Wang

Previous editions

This is the third edition of the workshop. Below you can find previous years' pages.
In particular, here you can find the PMLR proceedings of the final papers (proposal+experiments) from last year's edition.