1 code implementation • 26 Mar 2024 • Ehsan Sabouni, H. M. Sabbir Ahmad, Vittorio Giammarino, Christos G. Cassandras, Ioannis Ch. Paschalidis, Wenchao Li
Unfortunately, both performance and solution feasibility can be significantly impacted by two key factors: (i) the selection of the cost function and associated parameters, and (ii) the calibration of parameters within the CBF-based constraints, which capture the trade-off between performance and conservativeness.
no code implementations • 13 Mar 2024 • Haoxing Tian, Ioannis Ch. Paschalidis, Alex Olshevsky
We consider a distributed setup for reinforcement learning, where each agent has a copy of the same Markov Decision Process but transitions are sampled from the corresponding Markov chain independently by each agent.
no code implementations • 29 Feb 2024 • Erhan Can Ozcan, Vittorio Giammarino, James Queeney, Ioannis Ch. Paschalidis
This paper investigates how to incorporate expert observations (without explicit information on expert actions) into a deep reinforcement learning setting to improve sample efficiency.
1 code implementation • 25 Jan 2024 • Erhan Can Ozcan, Berk Görgülü, Mustafa G. Baydogan, Ioannis Ch. Paschalidis
The most popular classification algorithms are designed to maximize classification accuracy during training.
no code implementations • 8 Dec 2023 • Haoxing Tian, Ioannis Ch. Paschalidis, Alex Olshevsky
Neural Temporal Difference (TD) Learning is an approximate temporal difference method for policy evaluation that uses a neural network for function approximation.
1 code implementation • 29 Sep 2023 • Vittorio Giammarino, James Queeney, Ioannis Ch. Paschalidis
We focus on the problem of imitation learning from visual observations, where the learning agent has access to videos of experts as its sole learning source.
no code implementations • 27 Sep 2023 • ZhiYu Zhang, Heng Yang, Ashok Cutkosky, Ioannis Ch. Paschalidis
Motivated by the pursuit of instance optimality, we propose a new algorithm that simultaneously achieves ($i$) the AdaGrad-style second order gradient adaptivity; and ($ii$) the comparator norm adaptivity also known as "parameter freeness" in the literature.
no code implementations • 21 Jun 2023 • Guoyao Shen, Boran Hao, Mengyu Li, Chad W. Farris, Ioannis Ch. Paschalidis, Stephan W. Anderson, Xin Zhang
However, the drawback of these structures is that they are not fully utilizing the information from both domains (k-space and image).
1 code implementation • 31 Jan 2023 • James Queeney, Erhan Can Ozcan, Ioannis Ch. Paschalidis, Christos G. Cassandras
Robustness and safety are critical for the trustworthy deployment of deep reinforcement learning.
1 code implementation • 29 Nov 2022 • Arsenii Mustafin, Alex Olshevsky, Ioannis Ch. Paschalidis
Our main result is a geometric convergence bound with predetermined learning rate of $1/8$, which is identical to the convergence bound available for SVRG in the convex setting.
no code implementations • 15 Oct 2022 • Ruidi Chen, Boran Hao, Ioannis Ch. Paschalidis
We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR), which could tolerate data contaminated by outliers.
no code implementations • 25 Sep 2022 • Vittorio Giammarino, James Queeney, Lucas C. Carstensen, Michael E. Hasselmo, Ioannis Ch. Paschalidis
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards.
2 code implementations • 28 Jun 2022 • James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras
Data-driven, learning-based control methods offer the potential to improve operations in complex systems, and model-free deep reinforcement learning represents a popular approach to data-driven control.
1 code implementation • 13 May 2022 • ZhiYu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
Practical online learning tasks are often naturally defined on unconstrained domains, where optimal algorithms for general convex losses are characterized by the notion of comparator adaptivity.
1 code implementation • 11 Mar 2022 • Vittorio Giammarino, Matthew F Dunne, Kylie N Moore, Michael E Hasselmo, Chantal E Stern, Ioannis Ch. Paschalidis
We show that the combination of IL and RL can match human results and that good performance strongly depends on combining the allocentric information with an egocentric representation of the environment.
no code implementations • 5 Nov 2021 • Taiyao Wang, Kyle R. Hansen, Joshua Loving, Ioannis Ch. Paschalidis, Helen van Aggelen, Eran Simhon
Antimicrobial resistance (AMR) is a risk for patients and a burden for the healthcare system.
1 code implementation • NeurIPS 2021 • James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras
In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient.
no code implementations • 20 Aug 2021 • Ruidi Chen, Ioannis Ch. Paschalidis
This monograph develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust Optimization (DRO) under the Wasserstein metric.
no code implementations • NeurIPS 2021 • Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
While it is possible to obtain a linear reduction in the variance by averaging all the stochastic gradients at every step, this requires a lot of communication between the workers and the server, which can dramatically reduce the gains from parallelism.
2 code implementations • 22 Mar 2021 • Vittorio Giammarino, Ioannis Ch. Paschalidis
This problem is referred to as hierarchical imitation learning and can be handled as an inference problem in a Hidden Markov Model, which is done via an Expectation-Maximization type algorithm.
no code implementations • 2 Feb 2021 • ZhiYu Zhang, Ashok Cutkosky, Ioannis Ch. Paschalidis
Next, considering a related problem called online learning with memory, we construct a novel strongly adaptive algorithm that uses our first contribution as a building block.
no code implementations • 19 Dec 2020 • James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras
In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data.
no code implementations • 9 Jul 2020 • Salomón Wollenstein-Betech, Christian Muise, Christos G. Cassandras, Ioannis Ch. Paschalidis, Yasaman Khazaeni
Usage of automated controllers which make decisions on an environment are widespread and are often based on black-box models.
no code implementations • 10 Jun 2020 • Ruidi Chen, Ioannis Ch. Paschalidis
We develop Distributionally Robust Optimization (DRO) formulations for Multivariate Linear Regression (MLR) and Multiclass Logistic Regression (MLG) when both the covariates and responses/labels may be contaminated by outliers.
no code implementations • 10 Jun 2020 • Ruidi Chen, Ioannis Ch. Paschalidis
We propose a Distributionally Robust Optimization (DRO) formulation with a Wasserstein-based uncertainty set for selecting grouped variables under perturbations on the data for both linear regression and classification problems.
no code implementations • 3 Jun 2020 • Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
While the initial analysis of Local SGD showed it needs $\Omega ( \sqrt{T} )$ communications for $T$ local gradient steps in order for the error to scale proportionately to $1/(nT)$, this has been successively improved in a string of papers, with the state-of-the-art requiring $\Omega \left( n \left( \mbox{ polynomial in log } (T) \right) \right)$ communications.
no code implementations • 28 Jun 2019 • Shi Pu, Alex Olshevsky, Ioannis Ch. Paschalidis
We provide a discussion of several recent results which, in certain scenarios, are able to overcome a barrier in distributed stochastic optimization for machine learning.
no code implementations • 6 Jun 2019 • Shi Pu, Alex Olshevsky, Ioannis Ch. Paschalidis
This paper is concerned with minimizing the average of $n$ cost functions over a network, in which agents may communicate and exchange information with their peers in the network.
no code implementations • 21 Mar 2019 • Taiyao Wang, Ioannis Ch. Paschalidis
We augment linear Support Vector Machine (SVM) classifiers by adding three important features: (i) we introduce a regularization constraint to induce a sparse classifier; (ii) we devise a method that partitions the positive class into clusters and selects a sparse SVM classifier for each cluster; and (iii) we develop a method to optimize the values of controllable variables in order to reduce the number of data points which are predicted to have an undesirable outcome, which, in our setting, coincides with being in the positive class.
no code implementations • 21 Mar 2019 • Taiyao Wang, Ioannis Ch. Paschalidis
We establish that as the number of training samples grows large, the MIP solution converges to the true coefficient vectors in the absence of noise.
1 code implementation • 9 Nov 2018 • Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
We consider the standard model of distributed optimization of a sum of functions $F(\bz) = \sum_{i=1}^n f_i(\bz)$, where node $i$ in a network holds the function $f_i(\bz)$.
Optimization and Control
1 code implementation • 24 Oct 2018 • Henghui Zhu, Ioannis Ch. Paschalidis, Amir Tahmasebi
Next, a bidirectional LSTM-CRF model is trained for clinical concept extraction using the contextual word embedding model.
no code implementations • 3 Jan 2018 • Theodora S. Brisimi, Tingting Xu, Taiyao Wang, Wuyang Dai, William G. Adams, Ioannis Ch. Paschalidis
To strike a balance between accuracy and interpretability of the prediction, which is important in a medical setting, we propose two novel methods: K-LRT, a likelihood ratio test-based method, and a Joint Clustering and Classification (JCC) method which identifies hidden patient clusters and adapts classifiers to each cluster.
no code implementations • 7 Jun 2017 • Ruidi Chen, Ioannis Ch. Paschalidis
We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers.
2 code implementations • 11 Mar 2017 • Jing Zhang, Ioannis Ch. Paschalidis
We develop a method to estimate from data travel latency cost functions in multi-class transportation networks, which accommodate different types of vehicles with very different characteristics (e. g., cars and trucks).
Systems and Control Optimization and Control 90C33, 90C90, 90C30
2 code implementations • 27 Feb 2017 • Jing Zhang, Ioannis Ch. Paschalidis
Under Markovian assumptions, we leverage a Central Limit Theorem (CLT) for the empirical measure in the test statistic of the composite hypothesis Hoeffding test so as to establish weak convergence results for the test statistic, and, thereby, derive a new estimator for the threshold needed by the test.
no code implementations • 21 Jan 2017 • Manjesh K. Hanawal, Hao liu, Henghui Zhu, Ioannis Ch. Paschalidis
We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs.
2 code implementations • 29 Oct 2016 • Jing Zhang, Sepideh Pourazarm, Christos G. Cassandras, Ioannis Ch. Paschalidis
In earlier work (Zhang et al., 2016) we used actual traffic data from the Eastern Massachusetts transportation network in the form of spatial average speeds and road segment flow capacities in order to estimate Origin-Destination (OD) flow demand matrices for the network.
Systems and Control 90B06
no code implementations • 19 Sep 2013 • Jing Wang, Daniel Rossell, Christos G. Cassandras, Ioannis Ch. Paschalidis
We present five methods to the problem of network anomaly detection.