Search Results for author: Shaddin Dughmi

Found 8 papers, 0 papers with code

Is Transductive Learning Equivalent to PAC Learning?

no code implementations8 May 2024 Shaddin Dughmi, Yusuf Kalayci, Grayson York

Our results imply that transductive and PAC learning are essentially equivalent for supervised learning with pseudometric losses in the realizable setting, and for binary classification in the agnostic setting.

Binary Classification Learning Theory +2

Transductive Sample Complexities Are Compact

no code implementations15 Feb 2024 Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

We demonstrate a compactness result holding broadly across supervised learning with a general class of loss functions: Any hypothesis class $H$ is learnable with transductive sample complexity $m$ precisely when all of its finite projections are learnable with sample complexity $m$.

Learning Theory PAC learning

Regularization and Optimal Multiclass Learning

no code implementations24 Sep 2023 Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng

We demonstrate that an agnostic version of the Hall complexity again characterizes error rates exactly, and exhibit an optimal learner using maximum entropy programs.

Transductive Learning

On the Distortion of Voting with Multiple Representative Candidates

no code implementations21 Nov 2017 Yu Cheng, Shaddin Dughmi, David Kempe

Our main result is a clean and tight characterization of positional voting rules that have constant expected distortion (independent of the number of candidates and the metric space).

Of the People: Voting Is More Effective with Representative Candidates

no code implementations4 May 2017 Yu Cheng, Shaddin Dughmi, David Kempe

However, we show that independence alone is not enough to achieve the upper bound: even when candidates are drawn independently, if the population of candidates can be different from the voters, then an upper bound of $2$ on the approximation is tight.

Mitigating the Curse of Correlation in Security Games by Entropy Maximization

no code implementations11 Mar 2017 Haifeng Xu, Milind Tambe, Shaddin Dughmi, Venil Loyd Noronha

To mitigate this issue, we propose to design entropy-maximizing defending strategies for spatio-temporal security games, which frequently suffer from CoC.

Scheduling

Security Games with Information Leakage: Modeling and Computation

no code implementations23 Apr 2015 Haifeng Xu, Albert X. Jiang, Arunesh Sinha, Zinovi Rabinovich, Shaddin Dughmi, Milind Tambe

Our experiments confirm the necessity of handling information leakage and the advantage of our algorithms.

Dynamic Pricing with Limited Supply

no code implementations20 Aug 2011 Moshe Babaioff, Shaddin Dughmi, Robert Kleinberg, Aleksandrs Slivkins

The performance guarantee for the same mechanism can be improved to $O(\sqrt{k} \log n)$, with a distribution-dependent constant, if $k/n$ is sufficiently small.

Multi-Armed Bandits

Cannot find the paper you are looking for? You can Submit a new open access paper.