A New Look at an Old Problem: A Universal Learning Approach to Linear Regression

12 May 2019

Papers citing "A New Look at an Old Problem: A Universal Learning Approach to Linear Regression"

23 / 23 papers shown

Title
High Dimensional Binary Classification under Label Shift: Phase Transition and Regularization Jiahui Cheng Minshuo Chen Hao Liu Tuo Zhao Wenjing Liao 44 0 0 01 Dec 2022
Beyond Ridge Regression for Distribution-Free Data Koby Bibas M. Feder 22 0 0 17 Jun 2022
Generalization for multiclass classification with overparameterized linear models Vignesh Subramanian Rahul Arya A. Sahai AI4CE 37 9 0 03 Jun 2022
Bias-variance decomposition of overparameterized regression with random linear features J. Rocks Pankaj Mehta 22 12 0 10 Mar 2022
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution Ananya Kumar Aditi Raghunathan Robbie Jones Tengyu Ma Percy Liang OODD 50 646 0 21 Feb 2022
Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection Koby Bibas M. Feder Tal Hassner OODD 39 24 0 18 Oct 2021
Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness Uriya Pesso Koby Bibas M. Feder AAML 24 2 0 04 Sep 2021
Mitigating deep double descent by concatenating inputs John Chen Qihan Wang Anastasios Kyrillidis BDL 13 3 0 02 Jul 2021
Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels Florian Dubost Erin Hong Max Pike Siddharth Sharma Siyi Tang Nandita Bhaskhar Christopher Lee-Messer D. Rubin NoLa 37 0 0 03 Jun 2021
The Geometry of Over-parameterized Regression and Adversarial Perturbations J. Rocks Pankaj Mehta AAML 19 8 0 25 Mar 2021
Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression Koby Bibas M. Feder 11 5 0 14 Feb 2021
Efficient Data-Dependent Learnability Yaniv Fogel T. Shapira M. Feder 8 0 0 20 Nov 2020
Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation Aurick Zhou Sergey Levine BDL OOD UQCV 6 13 0 05 Nov 2020
Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models J. Rocks Pankaj Mehta 25 41 0 26 Oct 2020
Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks Eshaan Nichani Adityanarayanan Radhakrishnan Caroline Uhler 34 9 0 19 Oct 2020
Learning, compression, and leakage: Minimising classification error via meta-universal compression principles F. Rosas P. Mediano Michael C. Gastpar 10 10 0 14 Oct 2020
Benign overfitting in ridge regression Alexander Tsigler Peter L. Bartlett 33 160 0 29 Sep 2020
Optimal Regularization Can Mitigate Double Descent Preetum Nakkiran Prayaag Venkat Sham Kakade Tengyu Ma 31 128 0 04 Mar 2020
More Data Can Hurt for Linear Regression: Sample-wise Double Descent Preetum Nakkiran 25 68 0 16 Dec 2019
Deep Double Descent: Where Bigger Models and More Data Hurt Preetum Nakkiran Gal Kaplun Yamini Bansal Tristan Yang Boaz Barak Ilya Sutskever 46 916 0 04 Dec 2019
Deep pNML: Predictive Normalized Maximum Likelihood for Deep Neural Networks Koby Bibas Yaniv Fogel M. Feder BDL 27 19 0 28 Apr 2019
Universal Supervised Learning for Individual Data Yaniv Fogel M. Feder FedML SSL 14 10 0 22 Dec 2018
Optimal ridge penalty for real-world high-dimensional data can be zero or negative due to the implicit ridge regularization D. Kobak Jonathan Lomond Benoit Sanchez 35 89 0 28 May 2018