Cover Image

Bernoulli-LoRA: A Theoretical Framework for Randomized Low-Rank Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sokolov, Igor, Sadiev, Abdurakhmon, Demidovich, Yury, Al-Qahtani, Fawaz S, Richtárik, Peter
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Unified Theory of Stochastic Proximal Point Methods without Smoothness
by: Richtárik, Peter, et al.
Published: (2024)

Better LMO-based Momentum Methods with Second-Order Information
by: Khirirat, Sarit, et al.
Published: (2025)

Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
by: Sadiev, Abdurakhmon, et al.
Published: (2025)

Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation
by: Malinovsky, Grigory, et al.
Published: (2024)

Differentially Private Random Block Coordinate Descent
by: Maranjyan, Artavazd, et al.
Published: (2024)

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
by: Sadiev, Abdurakhmon, et al.
Published: (2025)

SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
by: Karagulyan, Avetik, et al.
Published: (2024)

Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
by: Sadiev, Abdurakhmon, et al.
Published: (2026)

A Unified Primal-Dual Recipe for Accelerating Three-Operator Splitting Methods
by: Sadiev, Abdurakhmon, et al.
Published: (2026)

A Nesterov-Accelerated Primal-Dual Splitting Algorithm for Convex Nonsmooth Optimization
by: Condat, Laurent, et al.
Published: (2026)

Stochastic Proximal Point Methods for Monotone Inclusions under Expected Similarity
by: Sadiev, Abdurakhmon, et al.
Published: (2024)

MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes
by: Sokolov, Igor, et al.
Published: (2024)

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
by: Demidovich, Yury, et al.
Published: (2024)

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise
by: Gorbunov, Eduard, et al.
Published: (2023)

Tight Lower Bounds and Optimal Algorithms for Stochastic Nonconvex Optimization with Heavy-Tailed Noise
by: Fradin, Adrien, et al.
Published: (2025)

MAST: Model-Agnostic Sparsified Training
by: Demidovich, Yury, et al.
Published: (2023)

Correlated Quantization for Faster Nonconvex Distributed Optimization
by: Panferov, Andrei, et al.
Published: (2024)

EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback
by: Fatkhullin, Ilyas, et al.
Published: (2021)

Stochastic Gradient Methods with Preconditioned Updates
by: Sadiev, Abdurakhmon, et al.
Published: (2022)

LoRA Training in the NTK Regime has No Spurious Local Minima
by: Jang, Uijeong, et al.
Published: (2024)

BiCoLoR: Communication-Efficient Optimization with Bidirectional Compression and Local Training
by: Condat, Laurent, et al.
Published: (2026)

Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
by: Zhang, Fangzhao, et al.
Published: (2024)

LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning
by: Tastan, Nurbek, et al.
Published: (2025)

Towards a Better Theoretical Understanding of Independent Subnetwork Training
by: Shulgin, Egor, et al.
Published: (2023)

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
by: Tyurin, Alexander, et al.
Published: (2022)

Non-Euclidean Broximal Point Method: A Blueprint for Geometry-Aware Optimization
by: Gruntkowska, Kaja, et al.
Published: (2025)

Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization
by: Condat, Laurent, et al.
Published: (2025)

Beyond the Ideal: Analyzing the Inexact Muon Update
by: Shulgin, Egor, et al.
Published: (2025)

Decentralized Personalized Federated Learning for Min-Max Problems
by: Borodich, Ekaterina, et al.
Published: (2021)

ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations
by: Gao, Yihang, et al.
Published: (2026)

Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle
by: Richtárik, Peter, et al.
Published: (2026)

Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
by: Gruntkowska, Kaja, et al.
Published: (2024)

Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
by: Tyurin, Alexander, et al.
Published: (2024)

LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression
by: Condat, Laurent, et al.
Published: (2024)

WeightLoRA: Keep Only Necessary Adapters
by: Veprikov, Andrey, et al.
Published: (2025)

Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation
by: Cui, Chengyu, et al.
Published: (2026)

On the Convergence of DP-SGD with Adaptive Clipping
by: Shulgin, Egor, et al.
Published: (2024)

First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
by: Shulgin, Egor, et al.
Published: (2025)

Muon is Provably Faster with Momentum Variance Reduction
by: Qian, Xun, et al.
Published: (2025)

Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning
by: Meinhardt, Georg, et al.
Published: (2024)