Chiyuan Zhang

Christopher A. Choquette-Choo

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

User-Level Differential Privacy With Few Examples Per User.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sparsity-Preserving Differentially Private Training of Large Embedding Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy.

[BibT_eX]

[DOI]

Nicholas Carlini

Proceedings of the 16th International Natural Language Generation Conference, 2023

Can Neural Network Memorization Be Localized?

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

On User-Level Private Convex Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Measuring Forgetting of Memorized Training Examples.

[BibT_eX]

[DOI]

Abhradeep Guha Thakurta

Nicolas Papernot

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Regression with Label Differential Privacy.

[BibT_eX]

[DOI]

Avinash V. Varadarajan

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Quantifying Memorization Across Neural Language Models.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Ticketed Learning-Unlearning Schemes.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Private Ad Modeling with DP-SGD.

[BibT_eX]

[DOI]

Avinash V. Varadarajan

Proceedings of the Workshop on Data Mining for Online Advertising (AdKDD 2023) co-located with the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 2023

2022

Are All Layers Created Equal?

[BibT_eX]

[DOI]

Christopher A. Choquette-Choo

Samy Bengio

Yoram Singer

J. Mach. Learn. Res., 2022

Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy.

[BibT_eX]

[DOI]

Nicholas Carlini

CoRR, 2022

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2022

Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation.

[BibT_eX]

[DOI]

Yao Qin

Ting Chen

Balaji Lakshminarayanan

Alex Beutel

Xuezhi Wang

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The Privacy Onion Effect: Memorization is Relative.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures.

[BibT_eX]

[DOI]

Emmanuel Abbe

Samy Bengio

Elisabetta Cornacchia

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Deduplicating Training Data Makes Language Models Better.

[BibT_eX]

[DOI]

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

2021

Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization.

[BibT_eX]

[DOI]

CoRR, 2021

Understanding deep learning (still) requires rethinking generalization.

[BibT_eX]

[DOI]

Commun. ACM, 2021

Do Vision Transformers See Like Convolutional Neural Networks?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Deep Learning with Label Differential Privacy.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Characterizing Structural Regularities of Labeled Data in Overparameterized Models.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Exploring the Memorization-Generalization Continuum in Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2020

What is being transferred in transfer learning?

[BibT_eX]

[DOI]

Behnam Neyshabur

Hanie Sedghi

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation.

[BibT_eX]

[DOI]

Vitaly Feldman

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Identity Crisis: Memorization and Generalization Under Extreme Overparameterization.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Transfusion: Understanding Transfer Learning with Applications to Medical Imaging.

[BibT_eX]

[DOI]

CoRR, 2019

Identity Crisis: Memorization and Generalization under Extreme Overparameterization.

[BibT_eX]

[DOI]

CoRR, 2019

Transfusion: Understanding Transfer Learning for Medical Imaging.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Novel Hierarchical Collaborative Method Based on Multi-objective Optimization for Modularization of Product Platform.

[BibT_eX]

[DOI]

Proceedings of the 23rd IEEE International Conference on Computer Supported Cooperative Work in Design, 2019

2018

Deep learning and structured data.

[BibT_eX]

[DOI]

PhD thesis, 2018

Unrestricted Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2018

A Study on Overfitting in Deep Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2018

Theory of Deep Learning IIb: Optimization Properties of SGD.

[BibT_eX]

[DOI]

CoRR, 2018

Machine Theory of Mind.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Decentralized State-Observer-Based Traffic Density Estimation of Large-Scale Urban Freeway Network by Dynamic Model.

[BibT_eX]

[DOI]

Yuqi Guo

Yangzhou Chen

Inf., 2017

Distributed state-observer-based traffic density estimation of urban freeway network.

[BibT_eX]

[DOI]

Proceedings of the 20th IEEE International Conference on Intelligent Transportation Systems, 2017

Understanding deep learning requires rethinking generalization.

[BibT_eX]

[DOI]

Proceedings of the 5th International Conference on Learning Representations, 2017

2016

A-Optimal Projection for Image Representation.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2016

Training Deep Nets with Sublinear Memory Cost.

[BibT_eX]

[DOI]

CoRR, 2016

2015

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems.

[BibT_eX]

[DOI]

CoRR, 2015

Learning with a Wasserstein Loss.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Discriminative template learning in group-convolutional networks for invariant speech representations.

[BibT_eX]

[DOI]

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

2014

Learning An Invariant Speech Representation.

[BibT_eX]

[DOI]

CoRR, 2014

Phone classification by a hierarchy of invariant representation layers.

[BibT_eX]

[DOI]

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Word-level invariant representations from acoustic waveforms.

[BibT_eX]

[DOI]

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

A deep representation for invariance and music classification.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

Image Compression by Learning to Minimize the Total Error.

[BibT_eX]

[DOI]

Xiaofei He

IEEE Trans. Circuits Syst. Video Technol., 2013

Parallel vector field embedding.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2013

Combining Active and Semi-Supervised Learning for Video Compression.

[BibT_eX]

[DOI]

Ming Ji

Int. J. Softw. Informatics, 2013

2012

Multi-task Vector Field Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

2011

A Variance Minimization Criterion to Feature Selection Using Laplacian Regularization.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2011

Semi-supervised Regression via Parallel Field Regularization.

[BibT_eX]

[DOI]

Binbin Lin

Xiaofei He

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Orthogonal Projection Analysis.

[BibT_eX]

[DOI]

Binbin Lin