Country
cf6501108fced72ee5c47e2151c4e153-Paper-Conference.pdf
Thus, most meta and transfer-learning HPO methods [7-16] consider a restrictive setting where all tasks must share the same set of hyperparameters so that the input data can be represented as fixed-sizedvectors.
DataAugmentationCanImproveRobustness
Finally,we evaluate our approach onCIFAR-10against` and`2 norm-bounded perturbations ofsize = 8/255 and =128/255,respectively.
Provably robust boosted decision stumps and trees against adversarial attacks
Maksym Andriushchenko, Matthias Hein
Neural Information Processing Systems http://nips.cc/
Facility Location Problem in Differential Privacy Model Revisited
Yunus Esencayi, Marco Gaboardi, Shi Li, Di Wang
Neural Information Processing Systems http://nips.cc/
Beta-CR Per Rob
L-layer W(i) 2 Rdi di 1 and b(i) 2 R simplicitydL =1 soW(L) is function f: Rd0!
PHYRE: A New Benchmark for Physical Reasoning
Anton Bakhtin, Laurens van der Maaten, Justin Johnson, Laura Gustafson, Ross Girshick
Understanding and reasoning about physics is a hallmark of intelligence [9].