Many robotics problems are formulated as optimization problems. However, most optimization solvers in robotics are locally optimal and the performance depends a lot on the initial guess. For challenging problems, the solver will often get stuck at poor loc ...
We consider the problem of enhancing user privacy in common data analysis and machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples from a generative adversarial network. We propose employing ...
Although encryption hides the content of communications from third parties, metadata, i.e., the information attached to the content (such as the size or timing of communication) can be a rich source of details and context. In this dissertation, we demonstr ...
Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribut ...
When applied to new datasets, acquired at different time moments, with different sensors or under different acquisition conditions, deep learning models might fail spectacularly. This is because they have learned from the data distribution observed during ...
Decentralized algorithms for stochastic optimization and learning rely on the diffusion of information through repeated local exchanges of intermediate estimates. Such structures are particularly appealing in situations where agents may be hesitant to shar ...
This paper considers the Byzantine fault-tolerance problem in distributed stochastic gradient descent (D-SGD) method - a popular algorithm for distributed multi-agent machine learning. In this problem, each agent samples data points independently from a ce ...
The aim of this thesis is to implement, analyze and improve the selected low noise clock
generation and distribution techniques for ADC implementations. The thesis is divided into
two parts. The first part focuses on the sampling phase generation and distr ...
Under the umbrella of smart toys, a myriad of interactive systems have addressed a variety of scenarios considering entertainment, education, sustainability, social and environmental learning through play. Tangibles and small toy robots prevail; but intera ...
In this thesis, we focus on the problem of achieving practical privacy guarantees in machine learning (ML), where the classic differential privacy (DP) fails to maintain a good trade-off between user privacy and data utility. Differential privacy guarantee ...
%0 Conference Paper %T Bayesian Differential Privacy for Machine Learning %A Aleksei Triastcyn %A Boi Faltings %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E A ...
