no code implementations • 4 Jul 2023 • Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna, Umut Simsekli
Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms.
no code implementations • 6 Mar 2023 • Sarah Sachs, Hedi Hadiji, Tim van Erven, Cristobal Guzman
In the fully adversarial case our bounds gracefully deteriorate to match the minimax regret.
no code implementations • 15 Feb 2022 • Sarah Sachs, Hédi Hadiji, Tim van Erven, Cristóbal Guzmán
case, our bounds match the rates one would expect from results in stochastic acceleration, and in the fully adversarial case they gracefully deteriorate to match the minimax regret.
no code implementations • 5 Jul 2021 • Tim van Erven, Sarah Sachs, Wouter M. Koolen, Wojciech Kotłowski
If the outliers are chosen adversarially, we show that a simple filtering strategy on extreme gradients incurs O(k) additive overhead compared to the usual regret bounds, and that this is unimprovable, which means that k needs to be sublinear in the number of rounds.
2 code implementations • 9 Nov 2015 • Shiry Ginosar, Kate Rakelly, Sarah Sachs, Brian Yin, Crystal Lee, Philipp Krahenbuhl, Alexei A. Efros
4) A new method for discovering and displaying the visual elements used by the CNN-based date-prediction model to date portraits, finding that they correspond to the tell-tale fashions of each era.