Cover Image

Accelerated Training through Iterative Gradient Propagation Along the Residual Path

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fagnou, Erwan, Caillon, Paul, Delattre, Blaise, Allauzen, Alexandre
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
by: Fagnou, Erwan, et al.
Published: (2026)

Chain and Causal Attention for Efficient Entity Tracking
by: Fagnou, Erwan, et al.
Published: (2024)

Bridging the Theoretical Gap in Randomized Smoothing
by: Delattre, Blaise, et al.
Published: (2025)

Forward Only Learning for Orthogonal Neural Networks of any Depth
by: Caillon, Paul, et al.
Published: (2025)

Fast Training of Recurrent Neural Networks with Stationary State Feedbacks
by: Caillon, Paul, et al.
Published: (2025)

Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity
by: Zhao, Hangyue, et al.
Published: (2026)

Conditional Distribution Quantization in Machine Learning
by: Delattre, Blaise, et al.
Published: (2025)

Spectral Norm of Convolutional Layers with Circular and Zero Paddings
by: Delattre, Blaise, et al.
Published: (2024)

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
by: Delattre, Blaise, et al.
Published: (2023)

Limits of Resolution Equivariance in Fourier Neural Operators
by: Colagrande, Alex, et al.
Published: (2026)

On the Stability of Neural Networks in Deep Learning
by: Delattre, Blaise
Published: (2025)

Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
by: Delattre, Blaise, et al.
Published: (2026)

Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics
by: Colagrande, Alex, et al.
Published: (2025)

Accelerating Neural Network Training Along Sharp and Flat Directions
by: Zakarin, Daniyar, et al.
Published: (2025)

Differentially Private Gradient Flow based on the Sliced Wasserstein Distance
by: Sebag, Ilana, et al.
Published: (2023)

Polynomial Mixing for Efficient Self-supervised Speech Encoders
by: Feillet, Eva, et al.
Published: (2026)

Exploring Precision and Recall to assess the quality and diversity of LLMs
by: Bronnec, Florian Le, et al.
Published: (2024)

GeoDirDock: Guiding Docking Along Geodesic Paths
by: Miñán, Raúl, et al.
Published: (2024)

PRISM: Parallel Residual Iterative Sequence Model
by: Jiang, Jie, et al.
Published: (2026)

Understanding Gradient Descent through the Training Jacobian
by: Belrose, Nora, et al.
Published: (2024)

Gradient Residual Connections
by: Pan, Yangchen, et al.
Published: (2026)

Improving Diversity in Language Models: When Temperature Fails, Change the Loss
by: Verine, Alexandre, et al.
Published: (2025)

On the MIA Vulnerability Gap Between Private GANs and Diffusion Models
by: Sebag, Ilana, et al.
Published: (2025)

GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction
by: Ferrini, Francesco, et al.
Published: (2025)

Quantum Equilibrium Propagation: Gradient-Descent Training of Quantum Systems
by: Scellier, Benjamin
Published: (2024)

Path-Sampled Integrated Gradients
by: Kamalov, Firuz, et al.
Published: (2026)

Iterate to Accelerate: A Unified Framework for Iterative Reasoning and Feedback Convergence
by: Fein-Ashley, Jacob
Published: (2025)

QF: Quick Feedforward AI Model Training without Gradient Back Propagation
by: Qi, Feng
Published: (2025)

DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
by: Chen, Yuen, et al.
Published: (2025)

Fast and Effective GNN Training through Sequences of Random Path Graphs
by: Bonchi, Francesco, et al.
Published: (2023)

Vanilla Gradient Descent for Oblique Decision Trees
by: Panda, Subrat Prasad, et al.
Published: (2024)

Path Gradients after Flow Matching
by: Vaitl, Lorenz, et al.
Published: (2025)

Accelerating Electron Dynamics Simulations through Machine Learned Time Propagators
by: Shah, Karan, et al.
Published: (2024)

Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation
by: Yamamoto, Kakei, et al.
Published: (2026)

Stacking as Accelerated Gradient Descent
by: Agarwal, Naman, et al.
Published: (2024)

Gradient Iterated Temporal-Difference Learning
by: Vincent, Théo, et al.
Published: (2026)

The Phase Is the Gradient: Equilibrium Propagation for Frequency Learning in Kuramoto Networks
by: Ahmadi, Mani Rash
Published: (2026)

Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation
by: Jantsch, Lasse Marten, et al.
Published: (2026)

Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
by: Niu, Xinlei, et al.
Published: (2023)

Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement
by: Zhu, Shuchen, et al.
Published: (2026)