Cover Image

When majority rules, minority loses: bias amplification of gradient descent

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bachoc, François, Bolte, Jérôme, Boustany, Ryan, Loubes, Jean-Michel
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A second-order-like optimizer with adaptive gradient scaling for deep learning
by: Bolte, Jérôme, et al.
Published: (2024)

On the numerical reliability of nonsmooth autodiff: a MaxPool case study
by: Boustany, Ryan
Published: (2024)

Geometry-induced Regularization in Deep ReLU Neural Networks
by: Bona-Pellissier, Joachim, et al.
Published: (2024)

Precise gradient descent training dynamics for finite-width multi-layer neural networks
by: Han, Qiyang, et al.
Published: (2025)

Gradient extremals, talwegs, valleys, and directional alignment for generic gradient descent
by: Bégout, Pascal, et al.
Published: (2026)

Recurrent neural networks: vanishing and exploding gradients are not the end of the story
by: Zucchet, Nicolas, et al.
Published: (2024)

Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity
by: Yang, Yan, et al.
Published: (2024)

Inexact subgradient methods for semialgebraic functions
by: Bolte, Jérôme, et al.
Published: (2024)

Scaling Laws of SignSGD in Linear Regression: When Does It Outperform SGD?
by: Kim, Jihwan, et al.
Published: (2026)

Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs
by: Ding, Dongsheng, et al.
Published: (2022)

New logarithmic step size for stochastic gradient descent
by: Shamaee, M. Soheil, et al.
Published: (2024)

Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks
by: Kiyani, Elham, et al.
Published: (2025)

Convergence of optimizers implies eigenvalues filtering at equilibrium
by: Bolte, Jerome, et al.
Published: (2025)

On the global convergence of gradient descent for wide shallow models with bounded nonlinearities
by: Petit, Romain, et al.
Published: (2026)

The duality structure gradient descent algorithm: analysis and applications to neural networks
by: Flynn, Thomas
Published: (2017)

Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks
by: Lafargue, Valentin, et al.
Published: (2025)

On the stability of gradient descent with second order dynamics for time-varying cost functions
by: Gibson, Travis E., et al.
Published: (2024)

Convergence of continuous-time stochastic gradient descent with applications to deep neural networks
by: Lugosi, Gabor, et al.
Published: (2024)

A stochastic gradient descent algorithm with random search directions
by: Gbaguidi, Eméric
Published: (2025)

Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression
by: Lok, Jackie, et al.
Published: (2024)

When and How Unlabeled Data Provably Improve In-Context Learning
by: Li, Yingcong, et al.
Published: (2025)

Natural gradient descent with momentum
by: Nouy, Anthony, et al.
Published: (2026)

Convergence of stochastic gradient descent under a local Lojasiewicz condition for deep neural networks
by: An, Jing, et al.
Published: (2023)

Learning Generative Dynamics with Soft Law Constraints: A McKean-Vlasov FBSDE Approach
by: Boustany, Samer El, et al.
Published: (2026)

gridfm-datakit-v1: A Python Library for Scalable and Realistic Power Flow and Optimal Power Flow Data Generation
by: Puech, Alban, et al.
Published: (2025)

On non-approximability of zero loss global ${\mathcal L}^2$ minimizers by gradient descent in Deep Learning
by: Chen, Thomas, et al.
Published: (2023)

Neural-Rendezvous: Provably Robust Guidance and Control to Encounter Interstellar Objects
by: Tsukamoto, Hiroyasu, et al.
Published: (2022)

Global convergence of gradient descent for phase retrieval
by: Fougereux, Théodore, et al.
Published: (2024)

Straight-Through meets Sparse Recovery: the Support Exploration Algorithm
by: Mohamed, Mimoun, et al.
Published: (2023)

A short proof of near-linear convergence of adaptive gradient descent under fourth-order growth and convexity
by: Davis, Damek, et al.
Published: (2026)

When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
by: Tao, Hongyi, et al.
Published: (2026)

Global $\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning
by: Chen, Thomas
Published: (2023)

SMiLE: Provably Enforcing Global Relational Properties in Neural Networks
by: Francobaldi, Matteo, et al.
Published: (2025)

Zeroth-Order Optimization Finds Flat Minima
by: Zhang, Liang, et al.
Published: (2025)

Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
by: Ghosh, Ipsita, et al.
Published: (2025)

GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
by: Zhao, Pengxiang, et al.
Published: (2025)

On Some Tunable Multi-fidelity Bayesian Optimization Frameworks
by: Manoj, Arjun, et al.
Published: (2025)

AI2STOW: End-to-End Deep Reinforcement Learning to Construct Master Stowage Plans under Demand Uncertainty
by: Van Twiller, Jaike, et al.
Published: (2025)

Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees
by: Ma, Jianhao, et al.
Published: (2025)

Closing the Loop: Coordinating Inventory and Recommendation via Deep Reinforcement Learning on Multiple Timescales
by: Jiang, Jinyang, et al.
Published: (2025)