Classification vs regression in overparameterized regimes: Does the loss function matter?

16 May 2020

Papers citing "Classification vs regression in overparameterized regimes: Does the loss function matter?"

43 / 93 papers shown

Title
Tight bounds for minimum l1-norm interpolation of noisy data Guillaume Wang Konstantin Donhauser Fanny Yang 79 20 0 10 Nov 2021
Harmless interpolation in regression and classification with structured features Andrew D. McRae Santhosh Karnik Mark A. Davenport Vidya Muthukumar 95 11 0 09 Nov 2021
Selective Regression Under Fairness Criteria Abhin Shah Yuheng Bu Joshua K. Lee Subhro Das Rameswar Panda P. Sattigeri G. Wornell 17 27 0 28 Oct 2021
On the Regularization of Autoencoders Harald Steck Dario Garcia-Garcia SSL AI4CE 22 4 0 21 Oct 2021
Towards Understanding the Data Dependency of Mixup-style Training Muthuraman Chidambaram Xiang Wang Yuzheng Hu Chenwei Wu Rong Ge UQCV 39 24 0 14 Oct 2021
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning Haiyun He Hanshu Yan Vincent Y. F. Tan 21 11 0 03 Oct 2021
Classification and Adversarial examples in an Overparameterized Linear Model: A Signal Processing Perspective Adhyyan Narang Vidya Muthukumar A. Sahai SILM AAML 26 1 0 27 Sep 2021
Reconstruction on Trees and Low-Degree Polynomials Frederic Koehler Elchanan Mossel 22 9 0 14 Sep 2021
A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning Yehuda Dar Vidya Muthukumar Richard G. Baraniuk 26 71 0 06 Sep 2021
Interpolation can hurt robust generalization even when there is no noise Konstantin Donhauser Alexandru cTifrea Michael Aerni Reinhard Heckel Fanny Yang 26 14 0 05 Aug 2021
Memorization in Deep Neural Networks: Does the Loss Function matter? Deep Patel P. Sastry TDI 6 8 0 21 Jul 2021
Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation Ke Wang Vidya Muthukumar Christos Thrampoulidis 20 47 0 21 Jun 2021
The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization Daniel LeJeune Hamid Javadi Richard G. Baraniuk 11 7 0 14 Jun 2021
Double Descent and Other Interpolation Phenomena in GANs Lorenzo Luzi Yehuda Dar Richard Baraniuk 15 5 0 07 Jun 2021
Towards an Understanding of Benign Overfitting in Neural Networks Zhu Li Zhi-Hua Zhou A. Gretton MLT 31 35 0 06 Jun 2021
Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation M. Belkin 9 182 0 29 May 2021
Support vector machines and linear regression coincide with very high-dimensional features Navid Ardeshir Clayton Sanford Daniel J. Hsu 8 21 0 28 May 2021
AdaBoost and robust one-bit compressed sensing Geoffrey Chinot Felix Kuchelmeister Matthias Löffler Sara van de Geer 27 5 0 05 May 2021
RATT: Leveraging Unlabeled Data to Guarantee Generalization Saurabh Garg Sivaraman Balakrishnan J. Zico Kolter Zachary Chase Lipton 25 29 0 01 May 2021
Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures Yuan Cao Quanquan Gu M. Belkin 4 51 0 28 Apr 2021
How rotational invariance of common kernels prevents generalization in high dimensions Konstantin Donhauser Mingqi Wu Fanny Yang 13 22 0 09 Apr 2021
Benign Overfitting of Constant-Stepsize SGD for Linear Regression Difan Zou Jingfeng Wu Vladimir Braverman Quanquan Gu Sham Kakade 8 62 0 23 Mar 2021
The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression Yehuda Dar Daniel LeJeune Richard G. Baraniuk MLT 19 5 0 09 Mar 2021
On the interplay between data structure and loss function in classification problems Stéphane dÁscoli Marylou Gabrié Levent Sagun Giulio Biroli 19 17 0 09 Mar 2021
Label-Imbalanced and Group-Sensitive Classification under Overparameterization Ganesh Ramachandra Kini Orestis Paraskevas Samet Oymak Christos Thrampoulidis 27 93 0 02 Mar 2021
Multiplicative Reweighting for Robust Neural Network Optimization Noga Bar Tomer Koren Raja Giryes OOD NoLa 11 9 0 24 Feb 2021
Understanding and Mitigating Accuracy Disparity in Regression Jianfeng Chi Yuan Tian Geoffrey J. Gordon Han Zhao 13 25 0 24 Feb 2021
Distilling Double Descent Andrew Cotter A. Menon Harikrishna Narasimhan A. S. Rawat Sashank J. Reddi Yichen Zhou 12 7 0 13 Feb 2021
Interpolating Classifiers Make Few Mistakes Tengyuan Liang Benjamin Recht 14 28 0 28 Jan 2021
Mixed-Privacy Forgetting in Deep Networks Aditya Golatkar Alessandro Achille Avinash Ravichandran M. Polito Stefano Soatto CLL MU 127 159 0 24 Dec 2020
On the robustness of minimum norm interpolators and regularized empirical risk minimizers Geoffrey Chinot Matthias Löffler Sara van de Geer 21 20 0 01 Dec 2020
On Generalization of Adaptive Methods for Over-parameterized Linear Regression Vatsal Shah Soumya Basu Anastasios Kyrillidis Sujay Sanghavi AI4CE 17 4 0 28 Nov 2020
Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization Ke Wang Christos Thrampoulidis 15 27 0 18 Nov 2020
Benign overfitting in ridge regression Alexander Tsigler Peter L. Bartlett 13 159 0 29 Sep 2020
On the proliferation of support vectors in high dimensions Daniel J. Hsu Vidya Muthukumar Ji Xu 14 42 0 22 Sep 2020
Implicit Regularization via Neural Feature Alignment A. Baratin Thomas George César Laurent R. Devon Hjelm Guillaume Lajoie Pascal Vincent Simon Lacoste-Julien 13 6 0 03 Aug 2020
Prediction in latent factor regression: Adaptive PCR and beyond Xin Bing F. Bunea Seth Strimas-Mackey M. Wegkamp 17 2 0 20 Jul 2020
When Does Preconditioning Help or Hurt Generalization? S. Amari Jimmy Ba Roger C. Grosse Xuechen Li Atsushi Nitanda Taiji Suzuki Denny Wu Ji Xu 28 32 0 18 Jun 2020
Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks Like Hui M. Belkin UQCV AAML VLM 6 164 0 12 Jun 2020
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime Niladri S. Chatterji Philip M. Long 8 108 0 25 Apr 2020
Surprises in High-Dimensional Ridgeless Least Squares Interpolation Trevor Hastie Andrea Montanari Saharon Rosset R. Tibshirani 18 726 0 19 Mar 2019
Newton-MR: Inexact Newton Method With Minimum Residual Sub-problem Solver Fred Roosta Yang Liu Peng Xu Michael W. Mahoney 8 12 0 30 Sep 2018
High-dimensional generalized linear models and the lasso Sara van de Geer 189 750 0 04 Apr 2008