Martin Takáč

Newton Method Revisited: Global Convergence Rates up to $O(1/k^3)$ for Stepsize Schedules and Linesearch Procedures

$\psi$DAG: Projected Stochastic Approximation Iteration for Linear DAG Structure Learning

Exponential Objective Decrease in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness

$\psi$DAG: Projected Stochastic Approximation Iteration for Linear DAG Structure Learning

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity

$MirrorCheck$ : Efficient Adversarial Defense for Vision-Language Models

$\psi$DAG : Projected Stochastic Approximation Iteration for DAG Structure Learning