Fetching the paper…
Reading the bibliography…
We systematically study the calibration of classifiers trained with differentially private stochastic gradient descent (DP-SGD) and observe miscalibration across a wide range of vision and language tasks.
Roberta: A robustly optimized bert pretraining approach
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov · 1907
Earlier work this paper cites.
Are humans good intuitive statisticians after all? rethinking some conclusions from the literature on judgment under uncertainty
Leda Cosmides and John Tooby · 1996
Earlier work this paper cites.
Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods
John Platt et al · 1999
Earlier work this paper cites.
Transforming classifier scores into accurate multiclass probability estimates
Bianca Zadrozny and Charles Elkan · 2002
Earlier work this paper cites.
Calibrating noise to sensitivity in private data analysis
Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith · 2006
Earlier work this paper cites.
Stochastic gradient descent with differentially private updates
Shuang Song, Kamalika Chaudhuri, and Anand D Sarwate · 2013
Earlier work this paper cites.
Preserving statistical validity in adaptive data analysis
Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Aaron Leon Roth · 2015
Earlier work this paper cites.
Deep learning with differential privacy
Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Algorithmic stability for adaptive data analysis
Raef Bassily, Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, and Jonathan Ullman · 2016
Earlier work this paper cites.
Membership inference attacks against machine learning models
Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov · 2017
Earlier work this paper cites.
Logan: Membership inference attacks against generative models
Jamie Hayes, Luca Melis, George Danezis, and Emiliano De Cristofaro · 2017
Earlier work this paper cites.
On fairness and calibration
Geoff Pleiss, Manish Raghavan, Felix Wu, Jon Kleinberg, and Kilian Q Weinberger · 2017
Earlier work this paper cites.
Rényi differential privacy
Ilya Mironov · 2017
Earlier work this paper cites.
On calibration of modern neural networks
Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger · 2017
Earlier work this paper cites.
Multicalibration: Calibration for the (computationally-identifiable) masses
Ursula Hébert-Johnson, Michael Kim, Omer Reingold, and Guy Rothblum · 2018
Earlier work this paper cites.
SciTail: A textual entailment dataset from science question answering
Tushar Khot, Ashish Sabharwal, and Peter Clark · 2018
Cited alongside, same era.
Differential privacy has disparate impact on model accuracy
Eugene Bagdasaryan, Omid Poursaeed, and Vitaly Shmatikov · 2019
Cited alongside, same era.
Calibration: the achilles heel of predictive analytics
Ben Van Calster, David J McLernon, Maarten Van Smeden, Laure Wynants, and Ewout W Steyerberg · 2019
Cited alongside, same era.
Multiaccuracy: Black-box post-processing for fairness in classification
Michael P Kim, Amirata Ghorbani, and James Zou · 2019
Cited alongside, same era.
Using pre-training can improve model robustness and uncertainty
Dan Hendrycks, Kimin Lee, and Mantas Mazeika · 2019
Cited alongside, same era.
Gaussian differential privacy
Jinshuo Dong, Aaron Roth, and Weijie J Su · 2019
Cited alongside, same era.
Moritz Knolle, Alexander Ziller, Dmitrii Usynin, Rickmer Braren, Marcus R Makowski, Daniel Rueckert, and Georgios Kaissis · 2021
Later among the works it cites.
Revisiting the calibration of modern neural networks
Matthias Minderer, Josip Djolonga, Rob Romijnders, Frances Hubis, Xiaohua Zhai, Neil Houlsby, Dustin Tran, and Mario Lucic · 2021
Later among the works it cites.
Differentially private learning needs better features (or much more data)
Florian Tramer and Dan Boneh · 2021
Later among the works it cites.
On the convergence and calibration of deep learning with differential privacy
Zhiqi Bu, Hua Wang, Qi Long, and Weijie J Su · 2021
Later among the works it cites.
Differentially private empirical risk minimization under the fairness lens
Cuong Tran, My Dinh, and Ferdinando Fioretto · 2021
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference
Tom McCoy, Ellie Pavlick, and Tal Linzen · 2019
Cited alongside, same era.
Do better imagenet models transfer better?
Simon Kornblith, Jonathon Shlens, and Quoc V Le · 2019
Cited alongside, same era.
Does learning require memorization? a short tale about a long tail
Vitaly Feldman · 2020
Cited alongside, same era.
An image is worth 16x16 words: Transformers for image recognition at scale
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al · 2020
Cited alongside, same era.
Calibration of pre-trained transformers
Shrey Desai and Greg Durrett · 2020
Cited alongside, same era.
Privacy preserving recalibration under domain shift
Rachel Luo, Shengjia Zhao, Jiaming Song, Jonathan Kuck, Stefano Ermon, and Silvio Savarese · 2020
Cited alongside, same era.
Later among the works it cites.
Anastasios N Angelopoulos, Stephen Bates, Tijana Zrnic, and Michael I Jordan · 2021
Later among the works it cites.
Numerical composition of differential privacy
Sivakanth Gopi, Yin Tat Lee, and Lukas Wutschitz · 2021
Later among the works it cites.
Opacus: User-friendly differential privacy library in pytorch
Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, et al · 2021
Later among the works it cites.
How unfair is private learning ?
Amartya Sanyal, Yaxi Hu, and Fanny Yang · 2022
Closest in time.
What you see is what you get: Distributional generalization for algorithm design in deep learning
Bogdan Kulynych, Yao-Yuan Yang, Yaodong Yu, Jarosław Błasiok, and Preetum Nakkiran · 2022
Closest in time.
Unlocking high-accuracy differentially private image classification through scale
Soham De, Leonard Berrada, Jamie Hayes, Samuel L Smith, and Borja Balle · 2022
Closest in time.
Disparate impact in differential privacy from gradient misalignment
Maria S Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, and Jesse C Cresswell · 2022
Closest in time.
Language models (mostly) know what they know
Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield Dodds, Nova DasSarma, Eli Tran-Johnson, et al · 2022
Closest in time.
The calibration generalization gap
Annabelle Carrell, Neil Mallinar, James Lucas, and Preetum Nakkiran · 2022
Closest in time.