Search Results for author:
Found 39 papers, 15 papers with code
Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems
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.
One-Shot Averaging for Distributed TD($λ$) Under Markov Sampling
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.
A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations
This paper investigates how to incorporate expert observations (without explicit information on expert actions) into a deep reinforcement learning setting to improve sample efficiency.
Smooth Ranking SVM via Cutting-Plane Method
The most popular classification algorithms are designed to maximize classification accuracy during training.
On the Performance of Temporal Difference Learning With Neural Networks
Neural Temporal Difference (TD) Learning is an approximate temporal difference method for policy evaluation that uses a neural network for function approximation.
Adversarial Imitation Learning from Visual Observations using Latent Information
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.
Improving Adaptive Online Learning Using Refined Discretization
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.
Attention Hybrid Variational Net for Accelerated MRI Reconstruction
However, the drawback of these structures is that they are not fully utilizing the information from both domains (k-space and image).
Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees
Robustness and safety are critical for the trustworthy deployment of deep reinforcement learning.
Closing the gap between SVRG and TD-SVRG with Gradient Splitting
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.
Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers
We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR), which could tolerate data contaminated by outliers.
Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards.
Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse
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.
Optimal Comparator Adaptive Online Learning with Switching Cost
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.
Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task
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.
Predicting Antimicrobial Resistance in the Intensive Care Unit
Antimicrobial resistance (AMR) is a risk for patients and a burden for the healthcare system.
Generalized Proximal Policy Optimization with Sample Reuse
In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient.
Distributionally Robust Learning
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.
Communication-efficient SGD: From Local SGD to One-Shot Averaging
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.
Online Baum-Welch algorithm for Hierarchical Imitation Learning
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.
Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory
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.
Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approach
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.
Explainability of Intelligent Transportation Systems using Knowledge Compilation: a Traffic Light Controller Case
Usage of automated controllers which make decisions on an environment are widespread and are often based on black-box models.
Robustified Multivariate Regression and Classification Using Distributionally Robust Optimization under the Wasserstein Metric
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.
Robust Grouped Variable Selection Using Distributionally Robust Optimization
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.
Local SGD With a Communication Overhead Depending Only on the Number of Workers
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.
Asymptotic Network Independence in Distributed Stochastic Optimization for Machine Learning
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.
A Non-Asymptotic Analysis of Network Independence for Distributed Stochastic Gradient Descent
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.
Prescriptive Cluster-Dependent Support Vector Machines with an Application to Reducing Hospital Readmissions
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.
Convergence of Parameter Estimates for Regularized Mixed Linear Regression Models
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.
Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions
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
Clinical Concept Extraction with Contextual Word Embedding
Next, a bidirectional LSTM-CRF model is trained for clinical concept extraction using the contextual word embedding model.
Predicting Chronic Disease Hospitalizations from Electronic Health Records: An Interpretable Classification Approach
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.
A Robust Learning Algorithm for Regression Models Using Distributionally Robust Optimization under the Wasserstein Metric
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.
Data-Driven Estimation of Travel Latency Cost Functions via Inverse Optimization in Multi-Class Transportation Networks
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
Statistical Anomaly Detection via Composite Hypothesis Testing for Markov Models
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.
Learning Policies for Markov Decision Processes from Data
We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs.
Data-driven Estimation of Origin-Destination Demand and User Cost Functions for the Optimization of Transportation Networks
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
Network Anomaly Detection: A Survey and Comparative Analysis of Stochastic and Deterministic Methods
We present five methods to the problem of network anomaly detection.
