NeurIPS 2020 is the biggest conference on machine learning, with tons of content on differential privacy in many different forms. We were able to find two workshops, a competition, and 31 papers. This was just going off the preliminary accepted papers list, so it’s possible that we might have missed some papers on differential privacy – please let us know! We will update this post later, once all the conference material (papers and videos) are publicly available.

Workshops

• Privacy Preserving Machine Learning - PriML and PPML Joint Edition

• International Workshop on Scalability, Privacy, and Security in Federated Learning (SpicyFL 2020)

Competitions

• Hide-and-Seek Privacy Challenge: Synthetic Data Generation vs. Patient Re-identification with Clinical Time-series Data

Papers

• A Computational Separation between Private Learning and Online Learning
  Mark Bun

• Adversarially Robust Streaming Algorithms via Differential Privacy
  Avinatan Hasidim, Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer

• Auditing Differentially Private Machine Learning: How Private is Private SGD?
  Matthew Jagielski, Jonathan Ullman, Alina Oprea

• Bayesian Pseudocoresets
  Dionysis Manousakas, Zuheng Xu, Cecilia Mascolo, Trevor Campbell

• Breaking the Communication-Privacy-Accuracy Trilemma
  Wei-Ning Chen, Peter Kairouz, Ayfer Ozgur

• CoinPress: Practical Private Mean and Covariance Estimation
  Sourav Biswas, Yihe Dong, Gautam Kamath, Jonathan Ullman

• Differentially Private Clustering: Tight Approximation Ratios
  Badih Ghazi, Ravi Kumar, Pasin Manurangsi

• Differentially-Private Federated Linear Bandits
  Abhimanyu Dubey, Alex Pentland

• Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC
  Arun Ganesh, Kunal Talwar

• GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
  Dingfan Chen, Tribhuvanesh Orekondy, Mario Fritz

• Improving Sparse Vector Technique with Renyi Differential Privacy
  Yuqing Zhu, Yu-Xiang Wang

• Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms
  Hilal Asi, John Duchi

• Learning discrete distributions: user vs item-level privacy
  Yuhan Liu, Ananda Theertha Suresh, Felix Xinnan Yu, Sanjiv Kumar, Michael D Riley

• Learning from Mixtures of Private and Public Populations
  Raef Bassily, Shay Moran, Anupama Nandi

• Locally Differentially Private (Contextual) Bandits Learning
  Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, Liwei Wang

• Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms
  Thomas Berrett, Cristina Butucea

• On the Equivalence between Online and Private Learnability beyond Binary Classification
  Young Hun Jung, Baekjin Kim, Ambuj Tewari

• Optimal Private Median Estimation under Minimal Distributional Assumptions
  Christos Tzamos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Ilias Zadik

• Permute-and-Flip: A new mechanism for differentially-private selection
  Ryan McKenna, Daniel Sheldon

• Privacy Amplification via Random Check-Ins
  Borja Balle, Peter Kairouz, Brendan McMahan, Om Thakkar, Abhradeep Thakurta

• Private Identity Testing for High-Dimensional Distributions
  Clement Canonne, Gautam Kamath, Audra McMillan, Jonathan Ullman, Lydia Zakynthinou

• Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity
  Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia

• Smoothed Analysis of Online and Differentially Private Learning
  Nika Haghtalab, Tim Roughgarden, Abhishek Shetty

• Smoothly Bounding User Contributions in Differential Privacy
  Alessandro Epasto, Mohammad Mahdian, Jieming Mao, Vahab Mirrokni, Lijie Ren

• Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
  Raef Bassily, Vitaly Feldman, Cristobal Guzman, Kunal Talwar

• Synthetic Data Generators – Sequential and Private
  Olivier Bousquet, Roi Livni, Shay Moran

• The Discrete Gaussian for Differential Privacy
  Clement Canonne, Gautam Kamath, Thomas Steinke

• The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
  Adam Smith, Shuang Song, Abhradeep Thakurta

• Towards Better Generalization of Adaptive Gradient Methods
  Yingxue Zhou, Belhal Karimi, Jinxing Yu, Zhiqiang Xu, Ping Li

• Towards practical differentially private causal graph discovery
  Lun Wang, Qi Pang, Dawn Song

• Understanding Gradient Clipping in Private SGD: A Geometric Perspective
  Xiangyi Chen, Steven Wu, Mingyi Hong