Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks

16 June 2020

George Deligiannidis

Papers citing "Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks"

21 / 21 papers shown

Title
Generalization Guarantees for Multi-View Representation Learning and Application to Regularization via Gaussian Product Mixture Prior Milad Sefidgaran Abdellatif Zaidi Piotr Krasnowski 44 0 0 25 Apr 2025
Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors Milad Sefidgaran A. Zaidi Piotr Krasnowski 91 1 0 21 Feb 2025
Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets Benjamin Dupuis Paul Viallard George Deligiannidis Umut Simsekli 40 2 0 26 Apr 2024
Privacy of SGD under Gaussian or Heavy-Tailed Noise: Guarantees without Gradient Clipping Umut Simsekli Mert Gurbuzbalaban S. Yıldırım Lingjiong Zhu 38 2 0 04 Mar 2024
From Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGD Benjamin Dupuis Paul Viallard 18 3 0 01 Dec 2023
Generalization Guarantees via Algorithm-dependent Rademacher Complexity Sarah Sachs T. Erven Liam Hodgkinson Rajiv Khanna Umut Simsekli 23 3 0 04 Jul 2023
Deep neural networks architectures from the perspective of manifold learning German Magai AAML AI4CE 24 6 0 06 Jun 2023
Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks Xuanzhe Xiao Zengyi Li Chuanlong Xie Fengwei Zhou 21 3 0 06 Apr 2023
Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD than Constant Stepsize Mert Gurbuzbalaban Yuanhan Hu Umut Simsekli Lingjiong Zhu LRM 20 1 0 10 Feb 2023
Generalization Bounds with Data-dependent Fractal Dimensions Benjamin Dupuis George Deligiannidis Umut cSimcsekli AI4CE 35 12 0 06 Feb 2023
Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions Anant Raj Lingjiong Zhu Mert Gurbuzbalaban Umut Simsekli 26 15 0 27 Jan 2023
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States Ziqiao Wang Yongyi Mao 27 10 0 19 Nov 2022
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD Alireza Mousavi-Hosseini Sejun Park M. Girotti Ioannis Mitliagkas Murat A. Erdogdu MLT 324 48 0 29 Sep 2022
Trajectory-dependent Generalization Bounds for Deep Neural Networks via Fractional Brownian Motion Chengli Tan Jiang Zhang Junmin Liu 35 1 0 09 Jun 2022
Heavy-Tail Phenomenon in Decentralized SGD Mert Gurbuzbalaban Yuanhan Hu Umut Simsekli Kun Yuan Lingjiong Zhu 32 8 0 13 May 2022
Topology and geometry of data manifold in deep learning German Magai A. Ayzenberg AAML 19 11 0 19 Apr 2022
Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks Tolga Birdal Aaron Lou Leonidas J. Guibas Umut cSimcsekli 27 61 0 25 Nov 2021
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms A. Camuto George Deligiannidis Murat A. Erdogdu Mert Gurbuzbalaban Umut cSimcsekli Lingjiong Zhu 27 29 0 09 Jun 2021
Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent Kangqiao Liu Liu Ziyin Masakuni Ueda MLT 61 37 0 07 Dec 2020
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates Jeffrey Negrea Mahdi Haghifam Gintare Karolina Dziugaite Ashish Khisti Daniel M. Roy FedML 110 147 0 06 Nov 2019
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 119 577 0 27 Feb 2015