Sajad Fathi Hafshejani

Country flagCanada

Research Interests

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts before you send them.

Explore related searches

Articles (6)

Year:

2026

This paper presents a second examination of trigonometric step sizes and their impact on Warm Restart Stochastic Gradient Descent (SGD), an essential optimization technique in deep learning. Building on prior work with cosine-based step sizes, this study introduces three novel trigonometric step sizes aimed at enhancing warm restart methods. These step sizes are formulated to address the challenges posed by non-smooth and non-convex objective functions, ensuring that the algorithm can converge effectively toward the global minimum. Through rigorous theoretical analysis, we demonstrate that the proposed approach achieves an O1T convergence rate for smooth non-convex functions and extend the analysis to non-smooth and non-convex scenarios. Experimental evaluations on FashionMNIST, CIFAR10, and CIFAR100 datasets reveal significant improvements in test accuracy, including a notable 2.14% increase on CIFAR100 compared to existing warm restart strategies. These results underscore the effectiveness of trigonometric step sizes in enhancing optimization performance for deep learning models.

Year:

2025

A new two-step interior point method for solving linear programs is presented. The technique uses a convex combination of the auxiliary and central points to compute the search direction. To update the central point, we find the best value for step size such that the feasibility condition is held. Since we use the information from the previous iteration to find the search direction, the inverse of the system is evaluated only once every iteration. A detailed empirical evaluation is performed on NETLIB instances, which compares two variants of the approach to the primal-dual log barrier interior point method. Results show that the proposed method is faster. The method reduces the number of iterations and CPU time(s) by 27% and 18%, respectively, on NETLIB instances tested compared to the classical interior point algorithm.

Year:

2024

This paper proposes a novel sine step size for warm-restart stochastic gradient descent (SGD). For the SGD based on the new proposed step size, we establish convergence rates for smooth non-convex functions with and without the Polyak–Łojasiewicz (PL) condition. To assess the effectiveness of the new step size, we implemented it across several datasets, including FashionMNIST, CIFAR10, and CIFAR100. This implementation was compared against eight distinct existing methods. The experimental results demonstrate that the proposed sine step size improves the test accuracy of the CIFAR100 dataset by 1.14%. This improvement highlights the efficiency of the new step size when compared to eight other popular step size methods.

Year:

2024

We develop a hybrid classical–quantum method for solving the Lorenz system. We use the forward Euler method to discretize the system in time, transforming it into a system of equations. This set of equations is solved by using the Variational Quantum Linear Solver (VQLS) algorithm. We present numerical results comparing the hybrid method with the classical approach for solving the Lorenz system. The simulation results demonstrate that the VQLS method can effectively compute solutions comparable to classical methods. The method is easily extended to solving similar nonlinear differential equations.

Year:

2024

Year:

2023

Collaborators (1)

Daya Gaur

Professor of Computer Science

University of Lethbridge

CANADA
View details