CDS Accepted Papers at NeurIPS 2022

NYU Center for Data Science
3 min readNov 16, 2022

We’re excited to announce that many CDS faculty, researchers, and students will present at the upcoming thirty-sixth NeurIPS (Neural Information Processing Systems) Conference, taking place Monday, 11/28 through Friday, 12/9. The conference began in 1987 and focuses on the advancement of research in AI and machine learning. This year’s event will take place in a hybrid format — the first week will occur in-person at the New Orleans Ernest N. Morial Convention Center, and the second week will be virtual. Below is a comprehensive list of projects and their corresponding CDS participants (indicated in bold with asterisk in front of it):

A Data-Augmentation Is Worth A Thousand Samples” – Randall Balestriero · Ishan Misra · *Yann LeCun

Are All Losses Created Equal: A Neural Collapse Perspective” – Jinxin Zhou · Chong You · Xiao Li · *Kangning Liu · *Sheng Liu · Qing Qu · Zhihui Zhu

Asymptotics of smoothed Wasserstein distances in the small noise regime” – Yunzi Ding · *Jonathan Niles-Weed

Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers” – Wanqian Yang · *Polina Kirichenko · *Micah Goldblum · *Andrew Wilson

Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone” – Zi-Yi Dou · *Aishwarya Kamath · Zhe Gan · Pengchuan Zhang · Jianfeng Wang · Linjie Li · Zicheng Liu · Ce Liu · *Yann LeCun · Nanyun Peng · Jianfeng Gao · Lijuan Wang

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods” – Randall Balestriero · *Yann LeCun

Distributional Convergence of the Sliced Wasserstein Process” – Jiaqi Xi · *Jonathan Niles-Weed

Dungeons and Data: A Large-Scale NetHack Dataset” – Eric Hambro · Roberta Raileanu · *Danielle Rothermel · Vegard Mella · Tim Rocktäschel · Heinrich Küttler · Naila Murray

Exponential Separations in Symmetric Neural Networks” – Aaron Zweig · *Joan Bruna

Generative multitask learning mitigates target-causing confounding” — *Taro Makino · *Krzysztof Geras · *Kyunghyun Cho

Learning single-index models with shallow neural networks” – *Alberto Bietti · *Joan Bruna · Clayton Sanford · Min Jae Song

Maximum a posteriori natural scene reconstruction from retinal ganglion cells with deep denoiser priors” — Eric Wu · Alexander Sher · Alan Litke · *Eero Simoncelli · E.J. Chichilnisky · Nora Brackbill

On Feature Learning in the Presence of Spurious Correlations” — Pavel Izmailov · *Polina Kirichenko · Nate Gruver · *Andrew Wilson

On Non-Linear operators for Geometric Deep Learning” – Grégoire Sergeant-Perthui · Jakob Maier · *Joan Bruna · Edouard Oyallon

On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification” — *Sanyam Kapoor · *Wesley Maddox · Pavel Izmailov · *Andrew Wilson

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization” — *Sanae Lotfi · *Sanyam Kapoor · Marc Finzi · *Andres Potapczynski · *Micah Goldblum · *Andrew Wilson

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors” — *Ravid Shwartz-Ziv · *Micah Goldblum · Hossein Souri · Sanyam Kapoor · Chen Zhu · *Yann LeCun · *Andrew Wilson

projUNN: efficient method for training deep networks with unitary matrices” – Bobak Kiani · Randall Balestriero · *Yann LeCun · Seth Lloyd

SeqPATE: Differentially Private Text Generation via Knowledge Distillation” — Zhiliang Tian · Yingxiu Zhao · Ziyue Huang · Yu-Xiang Wang · Nevin L. Zhang · *He He

StrokeRehab: A Benchmark Dataset for Sub-second Action Identification” — *Aakash Kaku · *Kangning Liu · Avinash Parnandi · *Haresh Rengaraj Rajamohan · *Kannan Venkataramanan · Anita Venkatesan · Audre Wirtanen · Natasha Pandit · Heidi Schambra · *Carlos Fernandez-Granda

The Effects of Regularization and Data Augmentation are Class Dependent” – Randall Balestriero · Leon Bottou · *Yann LeCun

Using natural language and program abstractions to instill human inductive biases in machines” — Sreejan Kumar · Carlos G. Correa · Ishita Dasgupta · Raja Marjieh · *Michael Y Hu · Robert Hawkins · Jonathan D Cohen · Nathaniel Daw · Karthik Narasimhan · Tom Griffiths

VICRegL: Self-Supervised Learning of Local Visual Features” – Adrien Bardes · *Jean Ponce · *Yann LeCun

What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness? – *Nikolaos Tsilivis · *Julia Kempe

When does return-conditioned supervised learning work for offline reinforcement learning?”– David Brandfonbrener · *Alberto Bietti · Jacob Buckman · Romain Laroche · *Joan Bruna

The conference’s preliminary presentation schedule can be found on the NeurIPS Schedule Overview page.



NYU Center for Data Science

Official account of the Center for Data Science at NYU, home of the Undergraduate, Master’s, and Ph.D. programs in Data Science.