@inproceedings{langley00, author = {P. Langley}, title = {Crafting Papers on Machine Learning}, year = {2000}, pages = {1207--1216}, editor = {Pat Langley}, booktitle = {Proceedings of the 17th International Conference on Machine Learning (ICML 2000)}, address = {Stanford, CA}, publisher = {Morgan Kaufmann} } @InProceedings{pmlr-v134-agrawal21a, title = {Regret Minimization in Heavy-Tailed Bandits}, author = {Agrawal, Shubhada and Juneja, Sandeep K. and Koolen, Wouter M.}, booktitle = {Proceedings of Thirty Fourth Conference on Learning Theory}, pages = {26--62}, year = {2021}, volume = {134}, series = {Proceedings of Machine Learning Research}, month = {15--19 Aug}, publisher = {PMLR} } @article{fan2025fragility, title={The fragility of optimized bandit algorithms}, author={Fan, Lin and Glynn, Peter W}, journal={Operations Research}, volume={73}, number={6}, pages={3173--3198}, year={2025}, publisher={INFORMS} } @article{panda2026regret, title={Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards}, author={Panda, Subhodip and Agrawal, Shubhada}, journal={arXiv preprint arXiv:2604.14876}, year={2026} } @article{robbins1974expected, title={The expected sample size of some tests of power one}, author={Robbins, Herbert and Siegmund, David}, journal={The Annals of Statistics}, volume={2}, number={3}, pages={415--436}, year={1974}, publisher={Institute of Mathematical Statistics} } @article{honda2015non, title={Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards.}, author={Honda, Junya and Takemura, Akimichi}, journal={J. Mach. Learn. Res.}, volume={16}, pages={3721--3756}, year={2015} } @article{agrawal2021optimal, title={Optimal best-arm identification methods for tail-risk measures}, author={Agrawal, Shubhada and Koolen, Wouter M and Juneja, Sandeep}, journal={Advances in Neural Information Processing Systems}, volume={34}, pages={25578--25590}, year={2021} } @inproceedings{agrawal2020optimal, title={Optimal $\delta$-Correct Best-Arm Selection for Heavy-Tailed Distributions}, author={Agrawal, Shubhada and Juneja, Sandeep and Glynn, Peter}, booktitle={Algorithmic Learning Theory}, pages={61--110}, year={2020}, organization={PMLR} } @article{burnetas1996optimal, title={Optimal adaptive policies for sequential allocation problems}, author={Burnetas, Apostolos N and Katehakis, Michael N}, journal={Advances in Applied Mathematics}, volume={17}, number={2}, pages={122--142}, year={1996}, publisher={Elsevier} } @article{lai1985asymptotically, title={Asymptotically efficient adaptive allocation rules}, author={Lai, Tze Leung and Robbins, Herbert}, journal={Advances in Applied Mathematics}, volume={6}, number={1}, pages={4--22}, year={1985}, publisher={Academic Press} } @TechReport{mitchell80, author = "T. M. Mitchell", title = "The Need for Biases in Learning Generalizations", institution = "Computer Science Department, Rutgers University", year = "1980", address = "New Brunswick, MA", } @phdthesis{kearns89, author = {M. J. Kearns}, title = {Computational Complexity of Machine Learning}, school = {Department of Computer Science, Harvard University}, year = {1989} } @Book{MachineLearningI, editor = "R. S. Michalski and J. G. Carbonell and T. M. Mitchell", title = "Machine Learning: An Artificial Intelligence Approach, Vol. I", publisher = "Tioga", year = "1983", address = "Palo Alto, CA" } @Book{DudaHart2nd, author = "R. O. Duda and P. E. Hart and D. G. Stork", title = "Pattern Classification", publisher = "John Wiley and Sons", edition = "2nd", year = "2000" } @misc{anonymous, title= {Suppressed for Anonymity}, author= {Author, N. N.}, year= {2021} } @InCollection{Newell81, author = "A. Newell and P. S. Rosenbloom", title = "Mechanisms of Skill Acquisition and the Law of Practice", booktitle = "Cognitive Skills and Their Acquisition", pages = "1--51", publisher = "Lawrence Erlbaum Associates, Inc.", year = "1981", editor = "J. R. Anderson", chapter = "1", address = "Hillsdale, NJ" } @Article{Samuel59, author = "A. L. Samuel", title = "Some Studies in Machine Learning Using the Game of Checkers", journal = "IBM Journal of Research and Development", year = "1959", volume = "3", number = "3", pages = "211--229" } @article{agrawal2025stopping, title={On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds}, author={Agrawal, Shubhada and Ramdas, Aaditya}, journal={arXiv preprint arXiv:2504.19952}, year={2025} } @incollection{wald1992sequential, title={Sequential tests of statistical hypotheses}, author={Wald, Abraham}, booktitle={Breakthroughs in statistics: Foundations and basic theory}, pages={256--298}, year={1992}, publisher={Springer} } @book{wald2004sequential, title={Sequential analysis}, author={Wald, Abraham}, year={2004}, publisher={Courier Corporation} } @article{wald1948optimum, title={Optimum character of the sequential probability ratio test}, author={Wald, Abraham and Wolfowitz, Jacob}, journal={The Annals of Mathematical Statistics}, pages={326--339}, year={1948}, publisher={JSTOR} } @article{darling1967iterated, title={Iterated logarithm inequalities}, author={Darling, Donald A and Robbins, Herbert}, journal={Proceedings of the National Academy of Sciences}, volume={57}, number={5}, pages={1188--1192}, year={1967} } @book{siegmund2013sequential, title={Sequential Analysis: Tests and Confidence Intervals}, author={Siegmund, David}, year={2013}, publisher={Springer Science \& Business Media} } @article{chernoff1992sequential, title={Sequential Design of Experiments}, author={Chernoff, Herman}, journal={Ann. Math. Statist.}, volume={30}, number={4}, pages={755--770}, year={1959} } @inproceedings{honda2010asymptotically, title={An Asymptotically Optimal Bandit Algorithm for Bounded Support Models.}, author={Honda, Junya and Takemura, Akimichi}, booktitle={COLT}, pages={67--79}, year={2010} } @book{gut2009stopped, title={Stopped random walks}, author={Gut, Allan}, year={2009}, publisher={Springer} } @article{mukhopadhyay2020asymptotic, title={Asymptotic Normality of Sequential Stopping Times with Applications: Confidence Intervals for an Exponential Mean}, author={Mukhopadhyay, Nitis}, journal={Calcutta Statistical Association Bulletin}, volume={72}, number={1}, pages={17--34}, year={2020}, publisher={SAGE Publications Sage India: New Delhi, India} } @book{asmussen2003applied, title={Applied probability and queues}, author={Asmussen, S{\o}ren}, year={2003}, publisher={Springer} } @phdthesis{agrawal2022bandits, url = {http://hdl.handle.net/10603/478863}, title = {Bandits with Heavy Tails: Algorithms Analysis and Optimality}, author = {Shubhada Agrawal}, copyright = {university}, year = {2023}, school = {Tata Institute of Fundamental Research}, language = {English}} @article{jourdan2022top, title={Top two algorithms revisited}, author={Jourdan, Marc and Degenne, R{\'e}my and Baudry, Dorian and de Heide, Rianne and Kaufmann, Emilie}, journal={Advances in Neural Information Processing Systems}, volume={35}, pages={26791--26803}, year={2022} } @inproceedings{anscombe1952large, title={Large-sample theory of sequential estimation}, author={Anscombe, Francis J}, booktitle={Mathematical Proceedings of the Cambridge Philosophical Society}, volume={48}, number={4}, pages={600--607}, year={1952}, organization={Cambridge University Press} } @article{deep2024asymptotically, title={Asymptotically optimal and computationally efficient average treatment effect estimation in A/B testing}, author={Deep, Vikas and Bassamboo, Achal and Juneja, Sandeep Kumar}, jorunal={Forty-first International Conference on Machine Learning}, year={2024} } @article{deep2025asymptotic, title={Asymptotic optimality theory of confidence intervals of the mean}, author={Deep, Vikas and Bassamboo, Achal and Juneja, Sandeep}, journal={arXiv preprint arXiv:2501.19126}, year={2025} } @article{wang2026almost, title={Almost sure null bankruptcy of testing-by-betting strategies}, author={Wang, Hongjian and Agrawal, Shubhada and Ramdas, Aaditya}, journal={arXiv preprint arXiv:2602.08888}, year={2026} } @book{billingsley2017probability, title={Probability and measure}, author={Billingsley, Patrick}, year={2017}, publisher={John Wiley \& Sons} }