no code implementations • 8 Mar 2023 • Song Bian, Xiating Ouyang, Zhiwei Fan, Paraschos Koutris
We present (i) a linear time algorithm in the number of entries in the dataset that decides whether a test point is certifiably robust for NBC, (ii) an algorithm that counts for each label, the number of cleaned datasets on which the NBC can be trained to predict that label, and (iii) an efficient optimal algorithm that poisons a clean dataset by inserting the minimum number of missing values such that a test point is not certifiably robust for NBC.
no code implementations • 13 Jan 2022 • Austen Z. Fan, Paraschos Koutris
For this setting, we establish a dichotomy in the complexity of certifying robustness w. r. t.
1 code implementation • NeurIPS 2019 • Mikhail Yurochkin, Zhiwei Fan, Aritra Guha, Paraschos Koutris, XuanLong Nguyen
We develop new models and algorithms for learning the temporal dynamics of the topic polytopes and related geometric objects that arise in topic model based inference.
no code implementations • NeurIPS 2018 • Lingjiao Chen, Hongyi Wang, Jinman Zhao, Dimitris Papailiopoulos, Paraschos Koutris
Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training.
no code implementations • 26 May 2018 • Lingjiao Chen, Paraschos Koutris, Arun Kumar
Finally, we conduct extensive experiments, which validate that the MBP framework can provide high revenue to the seller, high affordability to the buyer, and also operate on low runtime cost.