no code implementations • 21 Jun 2023 • Diego Ihara Centurion, Karine Chubarian, Bohan Fan, Francesco Sgherzi, Thiruvenkadam S Radhakrishnan, Anastasios Sidiropoulos, Angelo Straight
We propose a label poisoning attack on geometric data sets against $k$-nearest neighbor classification.
no code implementations • NeurIPS 2021 • Evan McCarty, Qi Zhao, Anastasios Sidiropoulos, Yusu Wang
This leads to a mixed algorithmic-ML framework, which we call NN-Baker that has the capacity to approximately solve a family of graph optimization problems (e. g, maximum independent set and minimum vertex cover) in time linear to input graph size, and only polynomial to approximation parameter.
1 code implementation • NAACL 2021 • Karine Chubarian, Abdul Rafae Khan, Anastasios Sidiropoulos, Jia Xu
Deep Learning-based NLP systems can be sensitive to unseen tokens and hard to learn with high-dimensional inputs, which critically hinder learning generalization.
no code implementations • 27 Apr 2020 • Bohan Fan, Diego Ihara Centurion, Neshat Mohammadi, Francesco Sgherzi, Anastasios Sidiropoulos, Mina Valizadeh
We study the problem of finding a mapping $f$ from a set of points into the real line, under ordinal triple constraints.
no code implementations • 25 Sep 2019 • Diego Ihara, Neshat Mohammadi, Anastasios Sidiropoulos
Learning Mahalanobis metric spaces is an important problem that has found numerous applications.
no code implementations • 24 May 2019 • Diego Ihara, Neshat Mohammadi, Francesco Sgherzi, Anastasios Sidiropoulos
Learning Mahalanobis metric spaces is an important problem that has found numerous applications.
no code implementations • 13 Jul 2018 • Diego Ihara Centurion, Neshat Mohammadi, Anastasios Sidiropoulos
We study the problem of supervised learning a metric space under discriminative constraints.
no code implementations • 28 Feb 2018 • Timothy Carpenter, Ilias Diakonikolas, Anastasios Sidiropoulos, Alistair Stewart
Prior to this work, no finite sample upper bound was known for this estimator in more than $3$ dimensions.