Search Results for author:
Found 15 papers, 5 papers with code
A Survey of Risk-Aware Multi-Armed Bandits
In several applications such as clinical trials and financial portfolio optimization, the expected value (or the average reward) does not satisfactorily capture the merits of a drug or a portfolio.
Online Estimation and Optimization of Utility-Based Shortfall Risk
We derive non-asymptotic bounds on the estimation error in the number of samples.
Statistically Robust, Risk-Averse Best Arm Identification in Multi-Armed Bandits
In this paper, we show that specialized algorithms that exploit such parametric information are prone to inconsistent learning performance when the parameter is misspecified.
Bandit algorithms: Letting go of logarithmic regret for statistical robustness
We study regret minimization in a stochastic multi-armed bandit setting and establish a fundamental trade-off between the regret suffered under an algorithm, and its statistical robustness.
Constrained regret minimization for multi-criterion multi-armed bandits
We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon.
A Framework for End-to-End Deep Learning-Based Anomaly Detection in Transportation Networks
We develop an end-to-end deep learning-based anomaly detection model for temporal data in transportation networks.
LSTM-Based Anomaly Detection: Detection Rules from Extreme Value Theory
In this paper, we explore various statistical techniques for anomaly detection in conjunction with the popular Long Short-Term Memory (LSTM) deep learning model for transportation networks.
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards
We also compare the error bounds for our distribution oblivious algorithms with those corresponding to standard non-oblivious algorithms.
Grids versus Graphs: Partitioning Space for Improved Taxi Demand-Supply Forecasts
To explore the Voronoi tessellation scheme, we propose the use of GraphLSTM (Graph-based LSTM), by representing the Voronoi spatial partitions as nodes on an arbitrarily structured graph.
Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions
We derive concentration bounds for CVaR estimates, considering separately the cases of light-tailed and heavy-tailed distributions.
Taxi Demand-Supply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks
We find that the LSTM model based on input features extracted from a variable-sized polygon tessellation yields superior performance over the LSTM model based on fixed-sized grid tessellation.
Concentration bounds for empirical conditional value-at-risk: The unbounded case
In several real-world applications involving decision making under uncertainty, the traditional expected value objective may not be suitable, as it may be necessary to control losses in the case of a rare but extreme event.
Taxi demand forecasting: A HEDGE based tessellation strategy for improved accuracy
We show that the hybrid tessellation strategy performs consistently better than either of the two strategies across the data sets considered, at multiple time scales, and with different performance metrics.
Bandit algorithms to emulate human decision making using probabilistic distortions
For the $K$-armed bandit setting, we derive an upper bound on the expected regret for our proposed algorithm, and then we prove a matching lower bound to establish the order-optimality of our algorithm.
Collaborative Learning of Stochastic Bandits over a Social Network
A key finding of this paper is that natural extensions of widely-studied single agent learning policies to the network setting need not perform well in terms of regret.
