Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thekumparampil, Kiran Koshy, Hiranandani, Gaurush, Kalantari, Kousha, Sabach, Shoham, Kveton, Branislav
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910764827148288
author Thekumparampil, Kiran Koshy
Hiranandani, Gaurush
Kalantari, Kousha
Sabach, Shoham
Kveton, Branislav
author_facet Thekumparampil, Kiran Koshy
Hiranandani, Gaurush
Kalantari, Kousha
Sabach, Shoham
Kveton, Branislav
contents We study learning of human preferences from a limited comparison feedback. This task is ubiquitous in machine learning. Its applications such as reinforcement learning from human feedback, have been transformational. We formulate this problem as learning a Plackett-Luce model over a universe of $N$ choices from $K$-way comparison feedback, where typically $K \ll N$. Our solution is the D-optimal design for the Plackett-Luce objective. The design defines a data logging policy that elicits comparison feedback for a small collection of optimally chosen points from all ${N \choose K}$ feasible subsets. The main algorithmic challenge in this work is that even fast methods for solving D-optimal designs would have $O({N \choose K})$ time complexity. To address this issue, we propose a randomized Frank-Wolfe (FW) algorithm that solves the linear maximization sub-problems in the FW method on randomly chosen variables. We analyze the algorithm, and evaluate it empirically on synthetic and open-source NLP datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19396
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe
Thekumparampil, Kiran Koshy
Hiranandani, Gaurush
Kalantari, Kousha
Sabach, Shoham
Kveton, Branislav
Machine Learning
Artificial Intelligence
Information Theory
Optimization and Control
We study learning of human preferences from a limited comparison feedback. This task is ubiquitous in machine learning. Its applications such as reinforcement learning from human feedback, have been transformational. We formulate this problem as learning a Plackett-Luce model over a universe of $N$ choices from $K$-way comparison feedback, where typically $K \ll N$. Our solution is the D-optimal design for the Plackett-Luce objective. The design defines a data logging policy that elicits comparison feedback for a small collection of optimally chosen points from all ${N \choose K}$ feasible subsets. The main algorithmic challenge in this work is that even fast methods for solving D-optimal designs would have $O({N \choose K})$ time complexity. To address this issue, we propose a randomized Frank-Wolfe (FW) algorithm that solves the linear maximization sub-problems in the FW method on randomly chosen variables. We analyze the algorithm, and evaluate it empirically on synthetic and open-source NLP datasets.
title Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe
topic Machine Learning
Artificial Intelligence
Information Theory
Optimization and Control
url https://arxiv.org/abs/2412.19396