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?"

50 / 93 papers shown

Title
Structural Entropy Guided Probabilistic Coding Xiang Huang Hao Peng Li Sun Hui Lin Chunyang Liu Jiang Cao Philip S. Yu 74 0 0 12 Dec 2024
Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning Ilya Kaufman Omri Azencot AI4TS 29 2 0 17 Oct 2024
Provable Weak-to-Strong Generalization via Benign Overfitting David X. Wu A. Sahai 58 6 0 06 Oct 2024
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality Marko Medvedev Gal Vardi Nathan Srebro 54 3 0 05 Sep 2024
EUR-USD Exchange Rate Forecasting Based on Information Fusion with Large Language Models and Deep Learning Methods Hongcheng Ding Xuanze Zhao Zixiao Jiang Shamsul Nahar Abdullah Deshinta Arrova Dewi 21 0 0 23 Aug 2024
First-Order Manifold Data Augmentation for Regression Learning Ilya Kaufman Omri Azencot 23 3 0 16 Jun 2024
Class-wise Activation Unravelling the Engima of Deep Double Descent Yufei Gu 28 0 0 13 May 2024
Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regime Kuo-Wei Lai Vidya Muthukumar 31 0 0 10 May 2024
On the Benefits of Over-parameterization for Out-of-Distribution Generalization Yifan Hao Yong Lin Difan Zou Tong Zhang OODD OOD 28 4 0 26 Mar 2024
Benign overfitting in leaky ReLU networks with moderate input dimension Kedar Karhadkar Erin E. George Michael Murray Guido Montúfar Deanna Needell MLT 35 2 0 11 Mar 2024
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance Chiraag Kaushik Ran Liu Chi-Heng Lin Amrit Khera Matthew Y Jin Wenrui Ma Vidya Muthukumar Eva L. Dyer 38 3 0 18 Feb 2024
Why do Random Forests Work? Understanding Tree Ensembles as Self-Regularizing Adaptive Smoothers Alicia Curth Alan Jeffares M. Schaar UQCV 34 11 0 02 Feb 2024
The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness Yifan Hao Tong Zhang AAML 19 4 0 19 Jan 2024
Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space Yufei Gu Xiaoqing Zheng T. Aste 35 3 0 20 Oct 2023
Transformers as Support Vector Machines Davoud Ataee Tarzanagh Yingcong Li Christos Thrampoulidis Samet Oymak 35 43 0 31 Aug 2023
Noisy Interpolation Learning with Shallow Univariate ReLU Networks Nirmit Joshi Gal Vardi Nathan Srebro 27 8 0 28 Jul 2023
A Unified Approach to Controlling Implicit Regularization via Mirror Descent Haoyuan Sun Khashayar Gatmiry Kwangjun Ahn Navid Azizan AI4CE 10 11 0 24 Jun 2023
Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models David X. Wu A. Sahai 21 2 0 23 Jun 2023
Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign? Erin E. George Michael Murray W. Swartworth Deanna Needell MLT 8 4 0 16 Jun 2023
Bayesian Analysis for Over-parameterized Linear Model via Effective Spectra Tomoya Wakayama Masaaki Imaizumi 47 1 0 25 May 2023
From Tempered to Benign Overfitting in ReLU Neural Networks Guy Kornowski Gilad Yehudai Ohad Shamir 18 12 0 24 May 2023
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension Moritz Haas David Holzmüller U. V. Luxburg Ingo Steinwart MLT 27 13 0 23 May 2023
New Equivalences Between Interpolation and SVMs: Kernels and Structured Features Chiraag Kaushik Andrew D. McRae Mark A. Davenport Vidya Muthukumar 20 2 0 03 May 2023
General Loss Functions Lead to (Approximate) Interpolation in High Dimensions Kuo-Wei Lai Vidya Muthukumar 16 5 0 13 Mar 2023
Benign Overfitting for Two-layer ReLU Convolutional Neural Networks Yiwen Kou Zi-Yuan Chen Yuanzhou Chen Quanquan Gu MLT 47 12 0 07 Mar 2023
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization Spencer Frei Gal Vardi Peter L. Bartlett Nathan Srebro 30 22 0 02 Mar 2023
Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation Luca Pesce Florent Krzakala Bruno Loureiro Ludovic Stephan 16 26 0 17 Feb 2023
Interpolation Learning With Minimum Description Length N. Manoj Nathan Srebro 17 4 0 14 Feb 2023
Sketched Ridgeless Linear Regression: The Role of Downsampling Xin Chen Yicheng Zeng Siyue Yang Qiang Sun 11 7 0 02 Feb 2023
$Tight bounds for maximum $\ell_1$-margin classifiers$ Tight bounds for maximum $\ell_1$ -margin classifiers Stefan Stojanovic Konstantin Donhauser Fanny Yang 32 0 0 07 Dec 2022
Margin-based sampling in high dimensions: When being active is less efficient than staying passive A. Tifrea Jacob Clarysse Fanny Yang 17 2 0 01 Dec 2022
Evaluating the Impact of Loss Function Variation in Deep Learning for Classification Simon Dräger Jannik Dunkelau 24 2 0 28 Oct 2022
A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models Lijia Zhou Frederic Koehler Pragya Sur Danica J. Sutherland Nathan Srebro 83 9 0 21 Oct 2022
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective Chi-Heng Lin Chiraag Kaushik Eva L. Dyer Vidya Muthukumar 19 26 0 10 Oct 2022
Deep Linear Networks can Benignly Overfit when Shallow Ones Do Niladri S. Chatterji Philip M. Long 13 8 0 19 Sep 2022
Intersection of Parallels as an Early Stopping Criterion Ali Vardasbi Maarten de Rijke Mostafa Dehghani MoMe 28 5 0 19 Aug 2022
SphereFed: Hyperspherical Federated Learning Xin Dong S. Zhang Ang Li H. T. Kung FedML 31 19 0 19 Jul 2022
A law of adversarial risk, interpolation, and label noise Daniel Paleka Amartya Sanyal NoLa AAML 13 9 0 08 Jul 2022
On how to avoid exacerbating spurious correlations when models are overparameterized Tina Behnia Ke Wang Christos Thrampoulidis 31 2 0 25 Jun 2022
Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence Margalit Glasgow Colin Wei Mary Wootters Tengyu Ma 36 5 0 16 Jun 2022
Generalization for multiclass classification with overparameterized linear models Vignesh Subramanian Rahul Arya A. Sahai AI4CE 19 9 0 03 Jun 2022
A Blessing of Dimensionality in Membership Inference through Regularization Jasper Tan Daniel LeJeune Blake Mason Hamid Javadi Richard G. Baraniuk 16 18 0 27 May 2022
Fast Rates for Noisy Interpolation Require Rethinking the Effects of Inductive Bias Konstantin Donhauser Nicolò Ruggeri Stefan Stojanovic Fanny Yang 10 20 0 07 Mar 2022
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data Spencer Frei Niladri S. Chatterji Peter L. Bartlett MLT 21 69 0 11 Feb 2022
Error Scaling Laws for Kernel Classification under Source and Capacity Conditions Hugo Cui Bruno Loureiro Florent Krzakala Lenka Zdeborová 38 10 0 29 Jan 2022
Kernel Methods and Multi-layer Perceptrons Learn Linear Models in High Dimensions Mojtaba Sahraee-Ardakan M. Emami Parthe Pandit S. Rangan A. Fletcher 20 9 0 20 Jan 2022
Towards Sample-efficient Overparameterized Meta-learning Yue Sun Adhyyan Narang Halil Ibrahim Gulluk Samet Oymak Maryam Fazel BDL 17 24 0 16 Jan 2022
Is Importance Weighting Incompatible with Interpolating Classifiers? Ke Alexander Wang Niladri S. Chatterji Saminul Haque Tatsunori Hashimoto 11 20 0 24 Dec 2021
Understanding Square Loss in Training Overparametrized Neural Network Classifiers Tianyang Hu Jun Wang Wenjia Wang Zhenguo Li UQCV AAML 25 19 0 07 Dec 2021
Minimax Supervised Clustering in the Anisotropic Gaussian Mixture Model: A new take on Robust Interpolation Stanislav Minsker M. Ndaoud Yiqiu Shen 25 4 0 13 Nov 2021