no code implementations • 12 May 2022 • Vincent Y. F. Tan, Prashanth L. A., Krishna Jagannathan
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.
1 code implementation • 16 Nov 2021 • Vishwajit Hegde, Arvind S. Menon, L. A. Prashanth, Krishna Jagannathan
We derive non-asymptotic bounds on the estimation error in the number of samples.
no code implementations • 28 Aug 2020 • Anmol Kagrecha, Jayakrishnan Nair, Krishna Jagannathan
In this paper, we show that specialized algorithms that exploit such parametric information are prone to inconsistent learning performance when the parameter is misspecified.
1 code implementation • 22 Jun 2020 • Kumar Ashutosh, Jayakrishnan Nair, Anmol Kagrecha, Krishna Jagannathan
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.
1 code implementation • 17 Jun 2020 • Anmol Kagrecha, Jayakrishnan Nair, Krishna Jagannathan
We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon.
no code implementations • 20 Nov 2019 • Neema Davis, Gaurav Raina, Krishna Jagannathan
We develop an end-to-end deep learning-based anomaly detection model for temporal data in transportation networks.
no code implementations • 13 Sep 2019 • Neema Davis, Gaurav Raina, Krishna Jagannathan
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.
1 code implementation • NeurIPS 2019 • Anmol Kagrecha, Jayakrishnan Nair, Krishna Jagannathan
We also compare the error bounds for our distribution oblivious algorithms with those corresponding to standard non-oblivious algorithms.
no code implementations • 18 Feb 2019 • Neema Davis, Gaurav Raina, Krishna Jagannathan
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.
no code implementations • ICML 2020 • Prashanth L. A., Krishna Jagannathan, Ravi Kumar Kolla
We derive concentration bounds for CVaR estimates, considering separately the cases of light-tailed and heavy-tailed distributions.
1 code implementation • 10 Dec 2018 • Neema Davis, Gaurav Raina, Krishna Jagannathan
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.
no code implementations • 6 Aug 2018 • Ravi Kumar Kolla, Prashanth L. A., Sanjay P. Bhat, Krishna Jagannathan
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.
no code implementations • 17 May 2018 • Neema Davis, Gaurav Raina, Krishna Jagannathan
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.
no code implementations • 30 Nov 2016 • Ravi Kumar Kolla, Prashanth L. A., Aditya Gopalan, Krishna Jagannathan, Michael Fu, Steve Marcus
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.
no code implementations • 29 Feb 2016 • Ravi Kumar Kolla, Krishna Jagannathan, Aditya Gopalan
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.