Gradient correlation is a key ingredient to accelerate SGD with momentum
Fuente:
arXiv
Saved in:
| Main Authors: | Hermant, Julien, Renaud, Marien, Aujol, Jean-François, Dossal, Charles, Rondepierre, Aude |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Study of the behaviour of Nesterov Accelerated Gradient in a non convex setting: the strongly quasar convex case
by: Hermant, Julien, et al.
Published: (2024)
by: Hermant, Julien, et al.
Published: (2024)
Continuized Nesterov Acceleration for Non-Convex Optimization
by: Hermant, Julien, et al.
Published: (2025)
by: Hermant, Julien, et al.
Published: (2025)
Continuized Nesterov Momentum Achieves the $O(\varepsilon^{-7/4})$ Complexity without Additional Mechanisms
by: Hermant, Julien, et al.
Published: (2026)
by: Hermant, Julien, et al.
Published: (2026)
Strong Convergence of FISTA Iterates under H{ö}lderian and Quadratic Growth Conditions
by: Aujol, Jean-François, et al.
Published: (2024)
by: Aujol, Jean-François, et al.
Published: (2024)
Heavy Ball Momentum for Non-Strongly Convex Optimization
by: Aujol, Jean-François, et al.
Published: (2024)
by: Aujol, Jean-François, et al.
Published: (2024)
Acceleration for Polyak-Łojasiewicz Functions with a Gradient Aiming Condition
by: Hermant, Julien
Published: (2026)
by: Hermant, Julien
Published: (2026)
Stochastic Adaptive Gradient Descent Without Descent
by: Aujol, Jean-François, et al.
Published: (2025)
by: Aujol, Jean-François, et al.
Published: (2025)
Optimization with First Order Algorithms
by: Dossal, Charles, et al.
Published: (2024)
by: Dossal, Charles, et al.
Published: (2024)
Projected Block Coordinate Descent for sparse spike estimation
by: Bénard, Pierre-Jean, et al.
Published: (2024)
by: Bénard, Pierre-Jean, et al.
Published: (2024)
On the Moreau envelope properties of weakly convex functions
by: Renaud, Marien, et al.
Published: (2025)
by: Renaud, Marien, et al.
Published: (2025)
A note on the convergence of RED algorithms under minimal hypotheses and open questions
by: Traonmilin, Yann, et al.
Published: (2026)
by: Traonmilin, Yann, et al.
Published: (2026)
From sparse recovery to plug-and-play priors, understanding trade-offs for stable recovery with generalized projected gradient descent
by: Joundi, Ali, et al.
Published: (2025)
by: Joundi, Ali, et al.
Published: (2025)
Optimality of a refraction strategy in the optimal dividends problem with absolutely continuous controls subject to Parisian ruin
by: Locas, Félix, et al.
Published: (2023)
by: Locas, Félix, et al.
Published: (2023)
SGD with memory: fundamental properties and stochastic acceleration
by: Yarotsky, Dmitry, et al.
Published: (2024)
by: Yarotsky, Dmitry, et al.
Published: (2024)
Demystifying SGD with Doubly Stochastic Gradients
by: Kim, Kyurae, et al.
Published: (2024)
by: Kim, Kyurae, et al.
Published: (2024)
Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
by: Orvieto, Antonio, et al.
Published: (2022)
by: Orvieto, Antonio, et al.
Published: (2022)
Convergence of SGD with momentum in the nonconvex case: A time window-based analysis
by: Qiu, Junwen, et al.
Published: (2024)
by: Qiu, Junwen, et al.
Published: (2024)
From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees
by: Xie, Shengping, et al.
Published: (2025)
by: Xie, Shengping, et al.
Published: (2025)
From Gradient Clipping to Normalization for Heavy Tailed SGD
by: Hübler, Florian, et al.
Published: (2024)
by: Hübler, Florian, et al.
Published: (2024)
Convergence Analysis of a Proximal Stochastic Denoising Regularization Algorithm
by: Renaud, Marien, et al.
Published: (2024)
by: Renaud, Marien, et al.
Published: (2024)
GPU-accelerated dynamic nonlinear optimization with ExaModels and MadNLP
by: Pacaud, François, et al.
Published: (2024)
by: Pacaud, François, et al.
Published: (2024)
AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent
by: Surjanovic, Nikola, et al.
Published: (2025)
by: Surjanovic, Nikola, et al.
Published: (2025)
From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
by: Gaucher, Renaud, et al.
Published: (2026)
by: Gaucher, Renaud, et al.
Published: (2026)
On the Set of Possible Minimizers of a Sum of Convex Functions
by: Zamani, Moslem, et al.
Published: (2024)
by: Zamani, Moslem, et al.
Published: (2024)
Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
by: Sun, Tao, et al.
Published: (2024)
by: Sun, Tao, et al.
Published: (2024)
Local SGD and Federated Averaging Through the Lens of Time Complexity
by: Fradin, Adrien, et al.
Published: (2025)
by: Fradin, Adrien, et al.
Published: (2025)
Last-Iterate Complexity of SGD for Convex and Smooth Stochastic Problems
by: Garrigos, Guillaume, et al.
Published: (2025)
by: Garrigos, Guillaume, et al.
Published: (2025)
SLowcal-SGD: Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
by: Dahan, Tehila, et al.
Published: (2023)
by: Dahan, Tehila, et al.
Published: (2023)
Making SGD Parameter-Free
by: Carmon, Yair, et al.
Published: (2022)
by: Carmon, Yair, et al.
Published: (2022)
On the Trajectories of SGD Without Replacement
by: Beneventano, Pierfrancesco
Published: (2023)
by: Beneventano, Pierfrancesco
Published: (2023)
Convergence and Inference of Stream SGD, with Applications to Queueing Systems and Inventory Control
by: Li, Xiang, et al.
Published: (2023)
by: Li, Xiang, et al.
Published: (2023)
Avoiding Bias in Clipped SGD for Overparameterized Models under Generalized Smoothness
by: Lobanov, Aleksandr, et al.
Published: (2026)
by: Lobanov, Aleksandr, et al.
Published: (2026)
Tradeoffs between convergence rate and noise amplification for momentum-based accelerated optimization algorithms
by: Mohammadi, Hesameddin, et al.
Published: (2022)
by: Mohammadi, Hesameddin, et al.
Published: (2022)
An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems
by: Zhang, Huiling, et al.
Published: (2023)
by: Zhang, Huiling, et al.
Published: (2023)
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
by: Tyurin, Alexander, et al.
Published: (2024)
by: Tyurin, Alexander, et al.
Published: (2024)
Inertial Bregman Proximal Gradient under Partial Smoothness
by: Godeme, Jean-Jacques
Published: (2025)
by: Godeme, Jean-Jacques
Published: (2025)
Optimality of a barrier strategy in a spectrally negative Lévy model with a level-dependent intensity of bankruptcy
by: Mata, Dante, et al.
Published: (2024)
by: Mata, Dante, et al.
Published: (2024)
Learning-rate-free Momentum SGD with Reshuffling Converges in Nonsmooth Nonconvex Optimization
by: Hu, Xiaoyin, et al.
Published: (2024)
by: Hu, Xiaoyin, et al.
Published: (2024)
Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions
by: Gaash, Ofir, et al.
Published: (2025)
by: Gaash, Ofir, et al.
Published: (2025)
Dimension-adapted Momentum Outscales SGD
by: Ferbach, Damien, et al.
Published: (2025)
by: Ferbach, Damien, et al.
Published: (2025)
Similar Items
-
Study of the behaviour of Nesterov Accelerated Gradient in a non convex setting: the strongly quasar convex case
by: Hermant, Julien, et al.
Published: (2024) -
Continuized Nesterov Acceleration for Non-Convex Optimization
by: Hermant, Julien, et al.
Published: (2025) -
Continuized Nesterov Momentum Achieves the $O(\varepsilon^{-7/4})$ Complexity without Additional Mechanisms
by: Hermant, Julien, et al.
Published: (2026) -
Strong Convergence of FISTA Iterates under H{ö}lderian and Quadratic Growth Conditions
by: Aujol, Jean-François, et al.
Published: (2024) -
Heavy Ball Momentum for Non-Strongly Convex Optimization
by: Aujol, Jean-François, et al.
Published: (2024)