9 papers
Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling
Daniil Medyakov, Gleb Molodtsov, Savelii Chezhegov +2
Stochastic optimization algorithms are widely used for machine learning with large-scale data. However, their convergence often suffers from non-vanishing variance. Variance Reduct…
Incorporating Preconditioning into Accelerated Approaches: Theoretical Guarantees and Practical Improvement
Stepan Trifonov, Leonid Levin, Savelii Chezhegov +1
Machine learning and deep learning are widely researched fields that provide solutions to many modern problems. Due to the complexity of new problems related to the size of dataset…
Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
Saleh Vatan Khah, Savelii Chezhegov, Shahrokh Farahmand +2
Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-taile…
Convergence of Clipped-SGD for Convex -Smooth Optimization with Heavy-Tailed Noise
Savelii Chezhegov, Aleksandr Beznosikov, Samuel Horváth +1
Gradient clipping is a widely used technique in Machine Learning and Deep Learning (DL), known for its effectiveness in mitigating the impact of heavy-tailed noise, which frequentl…
Aligning Distributionally Robust Optimization with Practical Deep Learning Needs
Dmitrii Feoktistov, Igor Ignashin, Andrey Veprikov +4
While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to di…
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov +5
Methods with adaptive stepsizes, such as AdaGrad and Adam, are essential for training modern Deep Learning models, especially Large Language Models. Typically, the noise in the sto…