Suriya Gunasekar

Caio César Teodoro Mendes

Yi Zhang

Jyoti Aneja

CoRR, 2023

(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability.

[BibT_eX]

[DOI]

CoRR, 2023

(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability.

[BibT_eX]

[DOI]

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

2022

How to Fine-Tune Vision Models with SGD.

[BibT_eX]

[DOI]

CoRR, 2022

Generalization to translation shifts: a study in architectures and augmentations.

[BibT_eX]

[DOI]

CoRR, 2022

Unveiling Transformers with LEGO: a synthetic reasoning task.

[BibT_eX]

[DOI]

CoRR, 2022

Data Augmentation as Feature Manipulation: a story of desert cows and grass cows.

[BibT_eX]

[DOI]

Ruoqi Shen

Sébastien Bubeck

CoRR, 2022

Data Augmentation as Feature Manipulation.

[BibT_eX]

[DOI]

Ruoqi Shen

Sébastien Bubeck

Proceedings of the International Conference on Machine Learning, 2022

Neural-Sim: Learning to Generate Training Data with NeRF.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm.

[BibT_eX]

[DOI]

Meena Jagadeesan

Ilya P. Razenshteyn

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent.

[BibT_eX]

[DOI]

Blake E. Woodworth

Gintare Karolina Dziugaite

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

NeurIPS 2020 Competition: Predicting Generalization in Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Mirrorless Mirror Descent: A More Natural Discretization of Riemannian Gradient Flow.

[BibT_eX]

[DOI]

Blake E. Woodworth

Gintare Karolina Dziugaite

CoRR, 2020

Implicit Regularization and Convergence for Weight Normalization.

[BibT_eX]

[DOI]

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

Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy.

[BibT_eX]

[DOI]

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

Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning.

[BibT_eX]

[DOI]

Natarajan Subramanyam

Carlos Lassance

Daniel M. Roy

Proceedings of the NeurIPS 2020 Competition and Demonstration Track, 2020

Kernel and Rich Regimes in Overparametrized Models.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2020

2019

Implicit Regularization of Normalization Methods.

[BibT_eX]

[DOI]

CoRR, 2019

Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Convergence of Gradient Descent on Separable Data.

[BibT_eX]

[DOI]

Mor Shpigel Nacson

Jason D. Lee

Pedro Henrique Pamplona Savarese

Daniel Soudry

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

The Implicit Bias of Gradient Descent on Separable Data.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2018

Convergence of Gradient Descent on Separable Data.

[BibT_eX]

[DOI]

CoRR, 2018

Implicit Bias of Gradient Descent on Linear Convolutional Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

On preserving non-discrimination when combining expert advice.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Characterizing Implicit Bias in Terms of Optimization Geometry.

[BibT_eX]

[DOI]

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

2017

Implicit Regularization in Matrix Factorization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Learning Non-Discriminatory Predictors.

[BibT_eX]

[DOI]

Blake E. Woodworth

Mesrob I. Ohannessian

Proceedings of the 30th Conference on Learning Theory, 2017

2016

Preference Completion from Partial Rankings.

[BibT_eX]

[DOI]

Oluwasanmi Koyejo

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization.

[BibT_eX]

[DOI]

Proceedings of the 1st Machine Learning in Health Care, 2016

2015

Unified View of Matrix Completion under General Structural Constraints.

[BibT_eX]

[DOI]

Arindam Banerjee

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

Consistent Collective Matrix Completion under Joint Low Rank Structure.

[BibT_eX]

[DOI]

Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, 2015

2014

Face Detection on Distorted Images Augmented by Perceptual Quality-Aware Features.

[BibT_eX]

[DOI]

Alan C. Bovik

IEEE Trans. Inf. Forensics Secur., 2014

Exponential Family Matrix Completion under Structural Constraints.

[BibT_eX]

[DOI]

Pradeep Ravikumar

Proceedings of the 31th International Conference on Machine Learning, 2014

Face detection on distorted images using perceptual quality-aware features.

[BibT_eX]

[DOI]

Alan C. Bovik

Proceedings of the Human Vision and Electronic Imaging XIX, 2014

2013

Noisy Matrix Completion Using Alternating Minimization.

[BibT_eX]

[DOI]

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2013

2012

Review quality aware collaborative filtering.

[BibT_eX]

[DOI]

Sindhu Raghavan