1 code implementation • 19 Jan 2022 • ZhiYu Zhang, Ashok Cutkosky, Ioannis Paschalidis
Unconstrained Online Linear Optimization (OLO) is a practical problem setting to study the training of machine learning models.
no code implementations • 27 Sep 2021 • Shahabeddin Sotudian, Ruidi Chen, Ioannis Paschalidis
We show that this is equivalent to a regularized regression problem with a matrix norm regularizer.
no code implementations • 27 Sep 2021 • Ruidi Chen, Boran Hao, Ioannis Paschalidis
We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR), which could tolerate data contaminated by outliers.
1 code implementation • COLING 2020 • Boran Hao, Henghui Zhu, Ioannis Paschalidis
Domain knowledge is important for building Natural Language Processing (NLP) systems for low-resource settings, such as in the clinical domain.
1 code implementation • 7 Oct 2020 • ZhiYu Zhang, Ioannis Paschalidis
Due to recent empirical successes, the options framework for hierarchical reinforcement learning is gaining increasing popularity.
1 code implementation • NeurIPS 2019 • Ruidi Chen, Ioannis Paschalidis
This paper develops a prediction-based prescriptive model for optimal decision making that (i) predicts the outcome under each action using a robust nonlinear model, and (ii) adopts a randomized prescriptive policy determined by the predicted outcomes.
no code implementations • 14 Nov 2018 • Ruidi Chen, Ioannis Paschalidis
We develop a prediction-based prescriptive model for learning optimal personalized treatments for patients based on their Electronic Health Records (EHRs).
no code implementations • 31 May 2017 • Henghui Zhu, Feng Nan, Ioannis Paschalidis, Venkatesh Saligrama
Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications.