From PAC to Instance-Optimal Sample Complexity in the Plackett-Luce Model

03/01/2019
by   Aadirupa Saha, et al.
0

We consider PAC learning for identifying a good item from subset-wise samples in probability models, with instance-dependent sample complexity performance. For the setting where subsets of a fixed size can be tested and top-ranked feedback is made available to the learner each time, we give the first (ϵ,δ)-PAC best item algorithm with an instance-dependent sample complexity bound. The algorithm relies on a wrapper that uses a weaker PAC algorithm with worst-case performance guarantees to adapt to the hardness of the input instance. The sample complexity is shown to be multiplicatively better depending on the length of rank-ordered feedback available in each subset play. We also give a new fixed-budget best-item algorithm for the model along with an error bound. Numerical results of simulations of the algorithms are reported.

READ FULL TEXT
research
10/23/2018

Active Ranking with Subset-wise Preferences

We consider the problem of probably approximately correct (PAC) ranking ...
research
07/13/2023

Nested Elimination: A Simple Algorithm for Best-Item Identification from Choice-Based Feedback

We study the problem of best-item identification from choice-based feedb...
research
02/19/2020

Best-item Learning in Random Utility Models with Subset Choices

We consider the problem of PAC learning the most valuable item from a po...
research
02/26/2020

Decidability of Sample Complexity of PAC Learning in finite setting

In this short note we observe that the sample complexity of PAC machine ...
research
08/22/2023

Consistency-Checking Problems: A Gateway to Parameterized Sample Complexity

Recently, Brand, Ganian and Simonov introduced a parameterized refinemen...
research
08/12/2018

PAC-Battling Bandits with Plackett-Luce: Tradeoff between Sample Complexity and Subset Size

We introduce the probably approximately correct (PAC) version of the pro...
research
08/23/2022

Convergence bounds for nonlinear least squares for tensor recovery

We consider the problem of approximating a function in general nonlinear...

Please sign up or login with your details

Forgot password? Click here to reset