Picture for Samarth Gupta

Samarth Gupta

Quasi-Newton policy gradient algorithms

Oct 12, 2021
Haoya Li, Samarth Gupta, Hsiangfu Yu, Lexing Ying, Inderjit Dhillon

Figure 1 for Quasi-Newton policy gradient algorithms

Figure 2 for Quasi-Newton policy gradient algorithms

Figure 3 for Quasi-Newton policy gradient algorithms

* 18 pages, 10 figures

Access Paper or Ask Questions

Best-Arm Identification in Correlated Multi-Armed Bandits

Sep 10, 2021
Samarth Gupta, Gauri Joshi, Osman Yağan

Figure 1 for Best-Arm Identification in Correlated Multi-Armed Bandits

Figure 2 for Best-Arm Identification in Correlated Multi-Armed Bandits

Figure 3 for Best-Arm Identification in Correlated Multi-Armed Bandits

Figure 4 for Best-Arm Identification in Correlated Multi-Armed Bandits

* IEEE Journal on Selected Areas in Information Theory (Volume: 2, Issue: 2, June 2021)

Access Paper or Ask Questions

Integer Programming-based Error-Correcting Output Code Design for Robust Classification

Oct 30, 2020
Samarth Gupta, Saurabh Amin

Figure 1 for Integer Programming-based Error-Correcting Output Code Design for Robust Classification

Figure 2 for Integer Programming-based Error-Correcting Output Code Design for Robust Classification

Figure 3 for Integer Programming-based Error-Correcting Output Code Design for Robust Classification

Figure 4 for Integer Programming-based Error-Correcting Output Code Design for Robust Classification

Access Paper or Ask Questions

Multi-Armed Bandits with Correlated Arms

Dec 03, 2019
Samarth Gupta, Shreyas Chaudhari, Gauri Joshi, Osman Yağan

Figure 1 for Multi-Armed Bandits with Correlated Arms

Figure 2 for Multi-Armed Bandits with Correlated Arms

Figure 3 for Multi-Armed Bandits with Correlated Arms

Figure 4 for Multi-Armed Bandits with Correlated Arms

* arXiv admin note: text overlap with arXiv:1808.05904 A special case of the model studied in this paper is presented in arXiv:1808.05904

Access Paper or Ask Questions

Active Distribution Learning from Indirect Samples

Aug 16, 2018
Samarth Gupta, Gauri Joshi, Osman Yağan

Figure 1 for Active Distribution Learning from Indirect Samples

Figure 2 for Active Distribution Learning from Indirect Samples

Figure 3 for Active Distribution Learning from Indirect Samples

Figure 4 for Active Distribution Learning from Indirect Samples

* Allerton Conference on Communication, Control and Computing, 2018

Access Paper or Ask Questions