High-dimensional limit theorems for SGD: Effective dynamics and critical scaling

8 June 2022

Papers citing "High-dimensional limit theorems for SGD: Effective dynamics and critical scaling"

45 / 45 papers shown

Title
A Theory of Initialisation's Impact on Specialisation Devon Jarvis Sebastian Lee Clémentine Dominé Andrew M. Saxe Stefano Sarao Mannelli CLL 67 2 0 04 Mar 2025
Understanding the Generalization Error of Markov algorithms through Poissonization Benjamin Dupuis Maxime Haddouche George Deligiannidis Umut Simsekli 42 0 0 11 Feb 2025
Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions Elisabetta Cornacchia Dan Mikulincer Elchanan Mossel 54 0 0 10 Feb 2025
A theoretical perspective on mode collapse in variational inference Roman Soletskyi Marylou Gabrié Bruno Loureiro DRL 24 2 0 17 Oct 2024
Shallow diffusion networks provably learn hidden low-dimensional structure Nicholas M. Boffi Arthur Jacot Stephen Tu Ingvar M. Ziemann DiffM 29 1 0 15 Oct 2024
A spring-block theory of feature learning in deep neural networks Chengzhi Shi Liming Pan Ivan Dokmanić AI4CE 36 1 0 28 Jul 2024
Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent Adrien Schertzer Loucas Pillaud-Vivien 16 0 0 02 Jul 2024
Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs Luca Arnaboldi Yatin Dandi Florent Krzakala Bruno Loureiro Luca Pesce Ludovic Stephan 43 1 0 04 Jun 2024
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks Stefano Sarao Mannelli Yaraslau Ivashinka Andrew M. Saxe Luca Saglietti 27 2 0 03 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
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms Elizabeth Collins-Woodfin Inbar Seroussi Begona García Malaxechebarría Andrew W. Mackenzie Elliot Paquette Courtney Paquette 18 1 0 30 May 2024
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training Anchit Jain Rozhin Nobahari A. Baratin Stefano Sarao Mannelli 32 4 0 28 May 2024
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes Zhenfeng Tu Santiago Aranguri Arthur Jacot 24 8 0 27 May 2024
High dimensional analysis reveals conservative sharpening and a stochastic edge of stability Atish Agarwala Jeffrey Pennington 38 3 0 30 Apr 2024
Sliding down the stairs: how correlated latent variables accelerate learning with neural networks Lorenzo Bardone Sebastian Goldt 30 7 0 12 Apr 2024
Faster Convergence for Transformer Fine-tuning with Line Search Methods Philip Kenneweg Leonardo Galli Tristan Kenneweg Barbara Hammer ODL 22 2 0 27 Mar 2024
Fundamental limits of Non-Linear Low-Rank Matrix Estimation Pierre Mergny Justin Ko Florent Krzakala Lenka Zdeborová 20 1 0 07 Mar 2024
From Zero to Hero: How local curvature at artless initial conditions leads away from bad minima Tony Bonnaire Giulio Biroli C. Cammarota 32 0 0 04 Mar 2024
Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features Rodrigo Veiga Anastasia Remizova Nicolas Macris 27 0 0 12 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 44 16 0 07 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 59 25 0 05 Feb 2024
Enhancing selectivity using Wasserstein distance based reweighing Pratik Worah OOD 48 0 0 21 Jan 2024
Should Under-parameterized Student Networks Copy or Average Teacher Weights? Berfin Simsek Amire Bendjeddou W. Gerstner Johanni Brea 25 6 0 03 Nov 2023
High-dimensional SGD aligns with emerging outlier eigenspaces Gerard Ben Arous Reza Gheissari Jiaoyang Huang Aukosh Jagannath 14 14 0 04 Oct 2023
Symmetric Single Index Learning Aaron Zweig Joan Bruna MLT 23 2 0 03 Oct 2023
Beyond Log-Concavity: Theory and Algorithm for Sum-Log-Concave Optimization Mastane Achab 11 1 0 26 Sep 2023
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem Margalit Glasgow MLT 69 13 0 26 Sep 2023
On the different regimes of Stochastic Gradient Descent Antonio Sclocchi M. Wyart 16 17 0 19 Sep 2023
Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape Persia Jana Kamali Pierfrancesco Urbani 11 6 0 09 Sep 2023
On Single Index Models beyond Gaussian Data Joan Bruna Loucas Pillaud-Vivien Aaron Zweig 8 10 0 28 Jul 2023
The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets Noam Levi Yaron Oz 27 4 0 26 Jun 2023
A Nested Matrix-Tensor Model for Noisy Multi-view Clustering M. Seddik Mastane Achab Henrique X. Goulart Merouane Debbah 9 1 0 31 May 2023
Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff Arthur Jacot MLT 16 13 0 30 May 2023
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time Yatin Dandi Florent Krzakala Bruno Loureiro Luca Pesce Ludovic Stephan MLT 32 25 0 29 May 2023
Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD Luca Arnaboldi Florent Krzakala Bruno Loureiro Ludovic Stephan MLT 23 3 0 29 May 2023
Hotelling Deflation on Large Symmetric Spiked Tensors M. Seddik J. H. D. M. Goulart M. Guillaud 13 1 0 20 Apr 2023
High-dimensional limit of one-pass SGD on least squares Elizabeth Collins-Woodfin Elliot Paquette 16 3 0 13 Apr 2023
High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance Krishnakumar Balasubramanian Promit Ghosal Ye He 23 5 0 03 Apr 2023
Gradient flow on extensive-rank positive semi-definite matrix denoising A. Bodin N. Macris 13 3 0 16 Mar 2023
Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression Bhavya Agrawalla Krishnakumar Balasubramanian Promit Ghosal 23 2 0 20 Feb 2023
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks Luca Arnaboldi Ludovic Stephan Florent Krzakala Bruno Loureiro MLT 25 31 0 12 Feb 2023
Learning Single-Index Models with Shallow Neural Networks A. Bietti Joan Bruna Clayton Sanford M. Song 160 67 0 27 Oct 2022
Rigorous dynamical mean field theory for stochastic gradient descent methods Cédric Gerbelot Emanuele Troiani Francesca Mignacco Florent Krzakala Lenka Zdeborova 17 26 0 12 Oct 2022
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example Xingyu Zhu Zixuan Wang Xiang Wang Mo Zhou Rong Ge 64 35 0 07 Oct 2022
Understanding Gradient Descent on Edge of Stability in Deep Learning Sanjeev Arora Zhiyuan Li A. Panigrahi MLT 75 88 0 19 May 2022