1 code implementation • 9 May 2023 • Georg Siedel, Weijia Shao, Silvia Vock, Andrey Morozov
In the field of adversarial robustness of image classifiers, robustness is commonly defined as the stability of a model to all input changes within a p-norm distance.
1 code implementation • 21 Nov 2022 • Weijia Shao, Fikret Sivrikaya, Sahin Albayrak
In this paper, we propose and analyse a family of generalised stochastic composite mirror descent algorithms.
1 code implementation • 9 Aug 2022 • Weijia Shao, Sahin Albayrak
In this paper, we propose and analyze algorithms for zeroth-order optimization of non-convex composite objectives, focusing on reducing the complexity dependence on dimensionality.
1 code implementation • 8 Aug 2022 • Weijia Shao, Fikret Sivrikaya, Sahin Albayrak
Furthermore, the algorithms have efficient implementations for popular composite objectives and constraints and can be converted to stochastic optimisation algorithms with the optimal accelerated rate for smooth objectives.
1 code implementation • 4 Jun 2019 • Weijia Shao, Christian Geißler, Fikret Sivrikaya
Motivated by the problem of tuning hyperparameters in machine learning, we present a new approach for gradually and adaptively optimizing an unknown function using estimated gradients.