The role of regularization in classification of high-dimensional noisy Gaussian mixture

26 February 2020

Lenka Zdeborová

Papers citing "The role of regularization in classification of high-dimensional noisy Gaussian mixture"

50 / 58 papers shown

Title
High-order Regularization for Machine Learning and Learning-based Control Xinghua Liu Ming Cao 54 0 0 13 May 2025
The Double Descent Behavior in Two Layer Neural Network for Binary Classification Chathurika S Abeykoon A. Beknazaryan Hailin Sang 139 1 0 27 Apr 2025
Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model O. Duranthon L. Zdeborová 116 0 0 03 Mar 2025
Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure Samet Demir Zafer Dogan MLT 94 0 0 02 Mar 2025
The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model Kaito Takanami Takashi Takahashi Ayaka Sakata 155 1 0 27 Jan 2025
Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model F.S. Pezzicoli V. Ros F.P. Landes M. Baity-Jesi 98 1 0 20 Jan 2025
A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs Kasimir Tanner Matteo Vilucchio Bruno Loureiro Florent Krzakala AAML 105 1 0 31 Dec 2024
Analysis of High-dimensional Gaussian Labeled-unlabeled Mixture Model via Message-passing Algorithm Xiaosi Gu Tomoyuki Obuchi 139 0 0 29 Nov 2024
Statistical Inference in Classification of High-dimensional Gaussian Mixture Hanwen Huang Peng Zeng 49 0 0 25 Oct 2024
When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study Tomoyuki Obuchi Toshiyuki Tanaka 134 0 0 09 Sep 2024
Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets Khen Cohen Noam Levi Yaron Oz BDL 79 1 0 28 May 2024
Restoring balance: principled under/oversampling of data for optimal classification Emanuele Loffredo Mauro Pastore Simona Cocco R. Monasson 112 9 0 15 May 2024
A replica analysis of under-bagging Takashi Takahashi 140 3 0 15 Apr 2024
One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression Reza Ghane D. Akhtiamov Babak Hassibi 57 1 0 16 Feb 2024
Asymptotics of feature learning in two-layer networks after one gradient-step Hugo Cui Luca Pesce Yatin Dandi Florent Krzakala Yue M. Lu Lenka Zdeborová Bruno Loureiro MLT 135 19 0 07 Feb 2024
A phase transition between positional and semantic learning in a solvable model of dot-product attention Hugo Cui Freya Behrens Florent Krzakala Lenka Zdeborová MLT 98 16 0 06 Feb 2024
Asymptotic generalization error of a single-layer graph convolutional network O. Duranthon L. Zdeborová MLT 92 2 0 06 Feb 2024
The twin peaks of learning neural networks Elizaveta Demyanenko Christoph Feinauer Enrico M. Malatesta Luca Saglietti 62 0 0 23 Jan 2024
Regularized Linear Regression for Binary Classification D. Akhtiamov Reza Ghane Babak Hassibi NoLa 78 3 0 03 Nov 2023
Efficient Learning of Minimax Risk Classifiers in High Dimensions Kartheek Bondugula Santiago Mazuelas Aritz Pérez Martínez 36 0 0 11 Jun 2023
Least Squares Regression Can Exhibit Under-Parameterized Double Descent Xinyue Li Rishi Sonthalia 117 3 0 24 May 2023
Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach Urte Adomaityte G. Sicuro P. Vivo 71 10 0 06 Apr 2023
Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture Minh-Toan Nguyen Romain Couillet 65 4 0 03 Mar 2023
Universality laws for Gaussian mixtures in generalized linear models Yatin Dandi Ludovic Stephan Florent Krzakala Bruno Loureiro Lenka Zdeborová FedML 102 23 0 17 Feb 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 98 28 0 17 Feb 2023
Homophily modulates double descent generalization in graph convolution networks Chengzhi Shi Liming Pan Hong Hu Ivan Dokmanić 107 9 0 26 Dec 2022
Neural networks trained with SGD learn distributions of increasing complexity Maria Refinetti Alessandro Ingrosso Sebastian Goldt UQCV 141 43 0 21 Nov 2022
Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes Liam Hodgkinson Christopher van der Heide Fred Roosta Michael W. Mahoney UQCV 83 6 0 14 Oct 2022
Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models Kaiyue Wen Jiaye Teng J.N. Zhang NoLa 58 5 0 01 Jun 2022
Gaussian Universality of Perceptrons with Random Labels Federica Gerace Florent Krzakala Bruno Loureiro Ludovic Stephan Lenka Zdeborová 107 24 0 26 May 2022
Fundamental limits to learning closed-form mathematical models from data Oscar Fajardo-Fontiveros I. Reichardt Harry R. De Los Ríos Jordi Duch Marta Sales-Pardo Roger Guimerà 98 19 0 06 Apr 2022
Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves David Bosch Ashkan Panahi Ayça Özçelikkale Devdatt Dubhash MLT 97 2 0 06 Apr 2022
Learning curves for the multi-class teacher-student perceptron Elisabetta Cornacchia Francesca Mignacco R. Veiga Cédric Gerbelot Bruno Loureiro Lenka Zdeborová 95 21 0 22 Mar 2022
Theoretical characterization of uncertainty in high-dimensional linear classification Lucas Clarté Bruno Loureiro Florent Krzakala Lenka Zdeborová 91 21 0 07 Feb 2022
Bayesian Inference with Nonlinear Generative Models: Comments on Secure Learning Ali Bereyhi Bruno Loureiro Florent Krzakala R. Muller H. Schulz-Baldes 81 2 0 19 Jan 2022
Optimal regularizations for data generation with probabilistic graphical models Arnaud Fanthomme Francesca Rizzato Simona Cocco R. Monasson 69 3 0 02 Dec 2021
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning Haiyun He Hanshu Yan Vincent Y. F. Tan 109 11 0 03 Oct 2021
A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning Yehuda Dar Vidya Muthukumar Richard G. Baraniuk 117 72 0 06 Sep 2021
Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions Bruno Loureiro G. Sicuro Cédric Gerbelot Alessandro Pacco Florent Krzakala Lenka Zdeborová 78 62 0 07 Jun 2021
Minimum complexity interpolation in random features models Michael Celentano Theodor Misiakiewicz Andrea Montanari 59 4 0 30 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 52 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 100 17 0 09 Mar 2021
Label-Imbalanced and Group-Sensitive Classification under Overparameterization Ganesh Ramachandra Kini Orestis Paraskevas Samet Oymak Christos Thrampoulidis 129 96 0 02 Mar 2021
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed Maria Refinetti Sebastian Goldt Florent Krzakala Lenka Zdeborová 92 74 0 23 Feb 2021
On the Inherent Regularization Effects of Noise Injection During Training Oussama Dhifallah Yue M. Lu 61 30 0 15 Feb 2021
Phase Transitions in Transfer Learning for High-Dimensional Perceptrons Oussama Dhifallah Yue M. Lu 96 20 0 06 Jan 2021
Solvable Model for Inheriting the Regularization through Knowledge Distillation Luca Saglietti Lenka Zdeborová 53 20 0 01 Dec 2020
Binary Classification of Gaussian Mixtures: Abundance of Support Vectors, Benign Overfitting and Regularization Ke Wang Christos Thrampoulidis 101 29 0 18 Nov 2020
Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View Christos Thrampoulidis Samet Oymak Mahdi Soltanolkotabi 73 43 0 16 Nov 2020
Precise Statistical Analysis of Classification Accuracies for Adversarial Training Adel Javanmard Mahdi Soltanolkotabi AAML 110 63 0 21 Oct 2020