Search Results for author:
Found 6 papers, 2 papers with code
High Probability Convergence of Stochastic Gradient Methods
Instead, we show high probability convergence with bounds depending on the initial distance to the optimal solution.
META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions
There, STORM utilizes recursive momentum to achieve the VR effect and is then later made fully adaptive in STORM+ [Levy et al., '21], where full-adaptivity removes the requirement for obtaining certain problem-specific parameters such as the smoothness of the objective and bounds on the variance and norm of the stochastic gradients in order to set the step size.
On the Convergence of AdaGrad(Norm) on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
Finally, we give new accelerated adaptive algorithms and their convergence guarantee in the deterministic setting with explicit dependency on the problem parameters, improving upon the asymptotic rate shown in previous works.
Adaptive Accelerated (Extra-)Gradient Methods with Variance Reduction
To address this problem, we propose two novel adaptive VR algorithms: Adaptive Variance Reduced Accelerated Extra-Gradient (AdaVRAE) and Adaptive Variance Reduced Accelerated Gradient (AdaVRAG).
On Adversarial Bias and the Robustness of Fair Machine Learning
Optimizing prediction accuracy can come at the expense of fairness.
Fast Genetic Algorithms
We prove that the $(1+1)$ EA with this heavy-tailed mutation rate optimizes any $\jump_{m, n}$ function in a time that is only a small polynomial (in~$m$) factor above the one stemming from the optimal rate for this $m$.
