skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • Home
  • Search Results
  • Page 1 of 1

Search for: All records

Award ID contains: 2047288

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; (, Proceedings of the 13th International Conference on Learning Representations (ICLR))
    Free, publicly-accessible full text available April 28, 2026
  2. ; ; ; (, Proceedings of the 13th International Conference on Learning Representations (ICLR))
    Free, publicly-accessible full text available April 28, 2026
  3. ; (, Proceedings of the 41st International Conference on Machine Learning)
    Accepted Manuscript Full Text Available
  4. ; (, The 41st International Conference on Machine Learning (ICML 2024))
    Accepted Manuscript Full Text Available
  5. ; ; ; (, International Conference on Machine Learning (ICML))
    Accepted Manuscript Full Text Available
  6. ; ; ; (, Innovations in Theoretical Computer Science (ITCS))
    Accepted Manuscript Full Text Available
  7. ; (, International Conference on Artificial Intelligence and Statistics (AISTATS))
    Accepted Manuscript Full Text Available
  8. ; (, International Conference on Artificial Intelligence and Statistics (AISTATS))
    Accepted Manuscript Full Text Available
  9. ; ; ; (, Advances in Neural Information Processing Systems 34 (NeurIPS 2021))
    We consider the online linear optimization problem, where at every step the algorithm plays a point x_t in the unit ball, and suffers loss for some cost vector c_t that is then revealed to the algorithm. Recent work showed that if an algorithm receives a "hint" h_t that has non-trivial correlation with c_t before it plays x_t, then it can achieve a logarithmic regret guarantee, improving on the classical sqrt(T) bound. In this work, we study the question of whether an algorithm really requires a hint at every time step. Somewhat surprisingly, we show that an algorithm can obtain logarithmic regret with just O(sqrt(T)) hints under a natural query model. We give two applications of our result, to the well-studied setting of optimistic regret bounds and to the problem of online learning with abstention. 
    more » « less
    Accepted Manuscript Full Text Available
  10. ; ; ; (, Proceedings of The 24th International Conference on Artificial Intelligence and Statistics)
    We consider the online linear optimization problem with movement costs, a variant of online learning in which the learner must not only respond to cost vectors c_t with points x_t in order to maintain low regret, but is also penalized for movement by an additional cost. Classically, simple algorithms that obtain the optimal sqrt(T) regret already are very stable and do not incur a significant movement cost. However, recent work has shown that when the learning algorithm is provided with weak "hint" vectors that have a positive correlation with the costs, the regret can be significantly improved to log(T). In this work, we study the stability of such algorithms, and provide matching upper and lower bounds showing that incorporating movement costs results in intricate tradeoffs logarithmic and sqrt(T) regret. 
    more » « less
    Accepted Manuscript Full Text Available