Image de couverture de livre

Unbiased Approximate Vector-Jacobian Products for Efficient Backpropagation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Bakong, Killian, Massoulié, Laurent, Oyallon, Edouard, Scaman, Kevin
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting
par: Philippenko, Constantin, et autres
Publié: (2024)

Adaptive collaboration for online personalized distributed learning with heterogeneous clients
par: Philippenko, Constantin, et autres
Publié: (2025)

Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles
par: Scaman, Kevin, et autres
Publié: (2023)

Cyclic Data Parallelism for Efficient Parallelism of Deep Neural Networks
par: Fournier, Louis, et autres
Publié: (2024)

Stabilizing Native Low-Rank LLM Pretraining
par: Janson, Paul, et autres
Publié: (2026)

DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
par: Morel, Rudy, et autres
Publié: (2025)

Learning with Shallow Neural Networks on Cluster-Structured Features
par: Cornacchia, Elisabetta, et autres
Publié: (2026)

Meta-learning of shared linear representations beyond well-specified linear regression
par: Even, Mathieu, et autres
Publié: (2025)

$μ$LO: Compute-Efficient Meta-Generalization of Learned Optimizers
par: Thérien, Benjamin, et autres
Publié: (2024)

Training Implicit Networks for Image Deblurring using Jacobian-Free Backpropagation
par: Liu, Linghai, et autres
Publié: (2024)

The feasibility of multi-graph alignment: a Bayesian approach
par: Vassaux, Louis, et autres
Publié: (2025)

Test-time Generalization for Physics through Neural Operator Splitting
par: Serrano, Louis, et autres
Publié: (2026)

Model Parallelism With Subnetwork Data Parallelism
par: Singh, Vaibhav, et autres
Publié: (2025)

On Non-Linear operators for Geometric Deep Learning
par: Sergeant-Perthuis, Grégoire, et autres
Publié: (2022)

PETRA: Parallel End-to-end Training with Reversible Architectures
par: Rivaud, Stéphane, et autres
Publié: (2024)

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
par: Fournier, Louis, et autres
Publié: (2024)

Flow Perturbation++: Multi-Step Unbiased Jacobian Estimation for High-Dimensional Boltzmann Sampling
par: Peng, Xin, et autres
Publié: (2026)

Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks
par: Robin, David A. R., et autres
Publié: (2025)

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
par: Fraboni, Yann, et autres
Publié: (2022)

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
par: Nabli, Adel, et autres
Publié: (2024)

When to Forget? Complexity Trade-offs in Machine Unlearning
par: Van Waerebeke, Martin, et autres
Publié: (2025)

End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation
par: Gelphman, Eric, et autres
Publié: (2025)

Efficient Deep Learning with Decorrelated Backpropagation
par: Dalm, Sander, et autres
Publié: (2024)

Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
par: Bars, Batiste Le, et autres
Publié: (2023)

Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA
par: Aguié, Pierre, et autres
Publié: (2026)

Correlation detection in trees for planted graph alignment
par: Ganassali, Luca, et autres
Publié: (2021)

Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
par: Even, Mathieu, et autres
Publié: (2024)

Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization
par: Even, Mathieu, et autres
Publié: (2021)

On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians
par: Gelphman, Eric, et autres
Publié: (2026)

Statistical limits of correlation detection in trees
par: Ganassali, Luca, et autres
Publié: (2022)

Efficient Backpropagation with Variance-Controlled Adaptive Sampling
par: Wang, Ziteng, et autres
Publié: (2024)

Graph Alignment via Birkhoff Relaxation
par: Varma, Sushil Mahavir, et autres
Publié: (2025)

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation
par: Yang, Yuchen, et autres
Publié: (2024)

Efficient Unbiased Sparsification
par: Barnes, Leighton, et autres
Publié: (2024)

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
par: Cyffers, Edwige, et autres
Publié: (2022)

Backpropagation Neural Tree
par: Ojha, Varun, et autres
Publié: (2022)

The Cost of Avoiding Backpropagation
par: Panchal, Kunjal, et autres
Publié: (2025)

Unbiased Online Curvature Approximation for Regularized Graph Continual Learning
par: Yin, Jie, et autres
Publié: (2025)

Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients
par: Van Waerebeke, Martin, et autres
Publié: (2026)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
par: Muthuraman, Mannmohan
Publié: (2025)