4 papers
On Measuring Localization of Shortcuts in Deep Networks
Nikita Tsoy, Nikola Konstantinov
Shortcuts, spurious rules that perform well during training but fail to generalize, present a major challenge to the reliability of deep networks (Geirhos et al., 2020). However, t…
PAC Learnability in the Presence of Performativity
Ivan Kirev, Lyuben Baltadzhiev, Nikola Konstantinov
Following the wide-spread adoption of machine learning models in real-world applications, the phenomenon of performativity, i.e. model-dependent shifts in the test distribution, be…
On the Impact of Performative Risk Minimization for Binary Random Variables
Nikita Tsoy, Ivan Kirev, Negin Rahimiyazdi +1
Performativity, the phenomenon where outcomes are influenced by predictions, is particularly prevalent in social contexts where individuals strategically respond to a deployed mode…
Incentivizing Truthful Collaboration in Heterogeneous Federated Learning
Dimitar Chakarov, Nikita Tsoy, Kristian Minchev +1
Federated learning (FL) is a distributed collaborative learning method, where multiple clients learn together by sharing gradient updates instead of raw data. However, it is well-k…