Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models

10 August 2017

Lenka Zdeborová

Papers citing "Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models"

50 / 142 papers shown

Title
Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime Francesco Camilli D. Tieplova Eleonora Bergamin Jean Barbier 135 0 0 06 May 2025
Survey on Algorithms for multi-index models Joan Bruna Daniel Hsu 31 0 0 07 Apr 2025
Accurate, provable, and fast nonlinear tomographic reconstruction: A variational inequality approach Mengqi Lou K. A. Verchand Sara Fridovich-Keil A. Pananjady 33 0 0 13 Mar 2025
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models Taj Jones-McCormick Aukosh Jagannath S. Sen 58 0 0 24 Feb 2025
Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery Filip Kovačević Yihan Zhang Marco Mondelli 70 0 0 03 Feb 2025
The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model Kaito Takanami Takashi Takahashi Ayaka Sakata 40 0 0 27 Jan 2025
Unifying AMP Algorithms for Rotationally-Invariant Models Songbin Liu Junjie Ma 77 0 0 02 Dec 2024
Pretrained transformer efficiently learns low-dimensional target functions in-context Kazusato Oko Yujin Song Taiji Suzuki Denny Wu 41 4 0 04 Nov 2024
On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance Jean Barbier Francesco Camilli Justin Ko Koki Okajima 34 5 0 04 Nov 2024
Universality of Estimator for High-Dimensional Linear Models with Block Dependency Toshiki Tsuda Masaaki Imaizumi 27 0 0 25 Oct 2024
Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens Vittorio Erba Emanuele Troiani Luca Biggio Antoine Maillard Lenka Zdeborová 23 0 0 24 Oct 2024
$Theoretical limits of descending $\ell_0$ sparse-regression ML algorithms$ Theoretical limits of descending $\ell_0$ sparse-regression ML algorithms Mihailo Stojnic 34 0 0 10 Oct 2024
Statistical Mechanics of Min-Max Problems Yuma Ichikawa Koji Hukushima 31 1 0 09 Sep 2024
Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics Alireza Mousavi-Hosseini Denny Wu Murat A. Erdogdu MLT AI4CE 35 6 0 14 Aug 2024
Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold Han Cui Zhiyuan Yu Jingbo Liu 39 0 0 15 Jul 2024
On Naive Mean-Field Approximation for high-dimensional canonical GLMs Soumendu Sundar Mukherjee Jiaze Qiu Subhabrata Sen 40 1 0 21 Jun 2024
Crafting Heavy-Tails in Weight Matrix Spectrum without Gradient Noise Vignesh Kothapalli Tianyu Pang Shenyang Deng Zongmin Liu Yaoqing Yang 40 3 0 07 Jun 2024
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit Jason D. Lee Kazusato Oko Taiji Suzuki Denny Wu MLT 87 21 0 03 Jun 2024
Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise Jean Barbier Francesco Camilli Marco Mondelli Yizhou Xu 32 2 0 31 May 2024
Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions Luca Arnaboldi Yatin Dandi Florent Krzakala Luca Pesce Ludovic Stephan 70 12 0 24 May 2024
Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods Yihan Zhang Marco Mondelli 43 3 0 22 May 2024
High-Dimensional Single-Index Models: Link Estimation and Marginal Inference Kazuma Sawaya Yoshimasa Uematsu Masaaki Imaizumi 45 2 0 27 Apr 2024
A replica analysis of under-bagging Takashi Takahashi 72 3 0 15 Apr 2024
Inferring Change Points in High-Dimensional Linear Regression via Approximate Message Passing Gabriel Arpino Xiaoqi Liu R. Venkataramanan 25 0 0 11 Apr 2024
From Zero to Hero: How local curvature at artless initial conditions leads away from bad minima Tony Bonnaire Giulio Biroli C. Cammarota 42 0 0 04 Mar 2024
Asymptotic Dynamics of Alternating Minimization for Bilinear Regression Koki Okajima Takashi Takahashi 19 2 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 35 11 0 06 Feb 2024
Asymptotic generalization error of a single-layer graph convolutional network O. Duranthon L. Zdeborová MLT 46 2 0 06 Feb 2024
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents Yatin Dandi Emanuele Troiani Luca Arnaboldi Luca Pesce Lenka Zdeborová Florent Krzakala MLT 66 26 0 05 Feb 2024
Universality in block dependent linear models with applications to nonparametric regression Samriddha Lahiry Pragya Sur 28 1 0 30 Dec 2023
Inferring the Graph of Networked Dynamical Systems under Partial Observability and Spatially Colored Noise Augusto Santos Diogo Rente Rui Seabra José M. F. Moura 18 1 0 18 Dec 2023
Learning the Causal Structure of Networked Dynamical Systems under Latent Nodes and Structured Noise Augusto Santos Diogo Rente Rui Seabra José M. F. Moura 19 4 0 10 Dec 2023
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training Yefan Zhou Tianyu Pang Keqin Liu Charles H. Martin Michael W. Mahoney Yaoqing Yang 42 7 0 01 Dec 2023
Benchmarking the optimization optical machines with the planted solutions N. Stroev N. Berloff Nir Davidson 35 0 0 12 Nov 2023
Fitting an ellipsoid to random points: predictions using the replica method Antoine Maillard Dmitriy Kunisky 28 2 0 02 Oct 2023
High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality Sining Chen Leonardo Defilippis Bruno Loureiro G. Sicuro 16 10 0 28 Sep 2023
Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models Song Mei Yuchen Wu DiffM 31 26 0 20 Sep 2023
Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective Davide Ghio Yatin Dandi Florent Krzakala Lenka Zdeborová DiffM 30 26 0 27 Aug 2023
Fundamental limits of overparametrized shallow neural networks for supervised learning Francesco Camilli D. Tieplova Jean Barbier 35 9 0 11 Jul 2023
Bayes optimal learning in high-dimensional linear regression with network side information Sagnik Nandy Subhabrata Sen 14 2 0 09 Jun 2023
Gibbs Sampling the Posterior of Neural Networks Giovanni Piccioli Emanuele Troiani Lenka Zdeborová 41 2 0 05 Jun 2023
Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers Matteo Vilucchio Emanuele Troiani Vittorio Erba Florent Krzakala 22 1 0 30 May 2023
Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD Luca Arnaboldi Florent Krzakala Bruno Loureiro Ludovic Stephan MLT 37 3 0 29 May 2023
Moment-Based Adjustments of Statistical Inference in High-Dimensional Generalized Linear Models Kazuma Sawaya Yoshimasa Uematsu Masaaki Imaizumi 34 2 0 28 May 2023
A Three-regime Model of Network Pruning Yefan Zhou Yaoqing Yang Arin Chang Michael W. Mahoney 31 10 0 28 May 2023
High-dimensional Asymptotics of Denoising Autoencoders Hugo Cui Lenka Zdeborová 16 13 0 18 May 2023
Mixed Regression via Approximate Message Passing Nelvin Tan R. Venkataramanan 19 7 0 05 Apr 2023
Neural-prior stochastic block model O. Duranthon L. Zdeborová 41 3 0 17 Mar 2023
Asymptotic Bayes risk of semi-supervised multitask learning on Gaussian mixture Minh-Toan Nguyen Romain Couillet 27 4 0 03 Mar 2023
Sharp thresholds in inference of planted subgraphs Elchanan Mossel Jonathan Niles-Weed Youngtak Sohn Nike Sun Ilias Zadik 10 6 0 28 Feb 2023