What’s coming up at NeurIPS 2021?

The thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021) is due to the kick-off on Monday 6 December, and run until Tuesday 14 December. There is a bumper programme of events, including invited talks, orals, tutorials, workshops, and socials.

Invited talks

There are eight keynote speakers this year.

Luis von Ahn – How Duolingo uses AI to assess, engage and teach better
Mary Gray – The banality of scale: a theory on the limits of modeling bias and fairness frameworks for social justice (and other lessons from the pandemic)
Daniel Kahneman – An interview
Peter Bartlett – Benign overfitting
Gabor Lugosi – Do we know how to estimate the mean?
Meredith Broussard – Gender, allyship & public interest technology
Figalli Alessio – Optimal transport: past, present, and future
Radhika Nagpal – The collective intelligence of army ants, and the robots they inspire

Workshops

There will be a total of 60 workshops:

• 2nd Workshop on Self-Supervised Learning: Theory and Practice
• Advances in Programming Languages and Neurosymbolic Systems (AIPLANS)
• Closing the Gap between Academia and Industry in Federated Learning: Challenges on Privacy, Fairness, Robustness, Personalization and Data Ownership
• Bayesian Deep Learning
• Math AI for Education (MATHAI4ED): Bridging the Gap Between Research and Smart Education
• AI for Science: Mind the Gaps
• Differentiable Programming Workshop
• Second Workshop on Quantum Tensor Networks in Machine Learning
• The Symbiosis of Deep Learning and Differential Equations
• Deep Generative Models and Downstream Applications
• Medical Imaging meets NeurIPS
• OPT 2021: Optimization for Machine Learning
• Machine Learning for Autonomous Driving
• 4th Robot Learning Workshop: Self-Supervised and Lifelong Learning
• Workshop on Human and Machine Decisions
• Causal Inference Challenges in Sequential DecisionMaking: Bridging Theory and Practice
• Safe and Robust Control of Uncertain Systems
• Your model is wrong: Robustness and misspecification in probabilistic modeling
• Physical Reasoning and Inductive Biases for the Real World
• Efficient Natural Language and Speech Processing (Models, Training, and Inference)
• Bridging the Gap: from Machine Learning Research to Clinical Practice
• Machine Learning Meets Econometrics (MLECON)
• Algorithmic Fairness through the lens of Causality and Robustness
• ImageNet: Past, Present, and Future.
• Optimal Transport and Machine Learning
• Machine Learning in Public Health
• Cooperative AI
• Workshop on Deep Learning and Inverse Problems
• Meaning in Context: Pragmatic Communication in Humans and Machines
• ML For Systems
• Human-Centered AI
• Learning in Presence of Strategic Behavior
• Decision-Making and Learning with Strategic Feedback
• Metacognition in the Age of AI: Challenges and Opportunities
• AI for Credible Elections: A Call to Action
• Shared Visual Representations in Human and Machine Intelligence
• The Political Economy of Reinforcement Learning Systems (PERLS)
• Deep Reinforcement Learning
• Privacy in Machine Learning (PriML) 2021
• Machine Learning for Creativity and Design
• Databases and AI (DBAI)
• Workshop on Pre-registration in ML
• Machine learning from ground truth: New medical imaging datasets for unsolved medical problems.
• CtrlGen: Controllable Generative Modeling in Language and Vision
• Out-of-distribution generalization and adaptation in natural and artificial intelligence
• eXplainable AI approaches for debugging and diagnosis
• Data Centric AI
• Ecological Theory of Reinforcement Learning: How Does Task Design Influence Agent Learning?
• Third Workshop on AI for Humanitarian Assistance and Disaster Response
• Distribution Shifts in Real-World Applications
• I (Still) Can’t Believe It’s Not Better
• Causal Inference & Machine Learning: Why now?
• Machine Learning and the Physical Sciences
• Machine Learning in Structural Biology
• Workshop on Meta-Learning
• Learning Meaningful Representations of Life (LMRL)
• Deployable Decision Making in Embodied Systems (DDM)
• Offline Reinforcement Learning
• Tackling Climate Change with Machine Learning
• Machine Learning for the Developing World (ML4D): Global Challenges

Find out more about the workshops here.

Affinity group workshops

The following affinity group workshops will take place during the conference:

• Black in AI workshop
• LatinX in AI Research at NeurIPS 2021
• Queer in AI
• New in ML
• Indigenous in AI
• Women in Machine Learning

Tutorials

For this year’s conference, the organisers opted for a total of 10 invitation-only tutorials.

• Cesar Mattos (Federal University of Ceará), Felipe Tobar (University of Chile): The Art of Gaussian Processes: Classical and Contemporary
• Irina Higgins (DeepMind), Toni Creswell (DeepMind) and Seb Racaniere (DeepMind): Do structural priors still matter in the age of transformers?
• Karen McKinnon (University of California, Los Angeles), Andrew Poppick (Carleton College): Machine Learning and Statistics for Climate Science
• Maria Schuld (Xanadu & University of KwaZulu Natal): Machine learning with quantum computers
• Lilian Weng (Open AI), Jong Wook Kim (Open AI): Self-supervised learning: self-prediction and contrastive learning
• Shirley Ho (Flatiron Institute & New York University & Princeton University) and Miles Cranmer (Princeton University): ML for Physics and Physics for ML
• Timnit Gebru (Black in AI), Emily Denton (Google): Beyond Fair ML: Towards Just, Equitable, and Accountable Machine Learning Systems
• Toshiyuki Ohtsuka (Kyoto University): Real-Time Optimization for Fast and Complex Control Systems
• Vukosi Marivate (University of Pretoria), David Adelani (Saarland University): A journey through the opportunity of Lower Resourced Natural Language Processing — An African Lens
• Wee Sun Lee (National University of Singapore): Message Passing in Machine Learning

Find out more about the tutorials here.

Other sessions and events

Orals
Spotlights
Accepted paper list
Demonstrations
Datasets and benchmarks track
Competition track
Socials

Lucy Smith , Managing Editor for AIhub.

Lucy Smith , Managing Editor for AIhub.