English
Related papers

Related papers: Comparing Few to Rank Many: Active Human Preferenc…

200 papers

Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the model with…

Artificial Intelligence · Computer Science 2025-10-20 Keertana Chidambaram , Karthik Vinary Seetharaman , Vasilis Syrgkanis

We propose a rank-$k$ variant of the classical Frank-Wolfe algorithm to solve convex optimization over a trace-norm ball. Our algorithm replaces the top singular-vector computation ($1$-SVD) in Frank-Wolfe with a top-$k$ singular-vector…

Machine Learning · Computer Science 2017-11-10 Zeyuan Allen-Zhu , Elad Hazan , Wei Hu , Yuanzhi Li

We develop and analyse a first-order algorithm for the A-optimal experimental design problem. The problem is first presented as a special case of a parametric family of optimal design problems for which duality results and optimality…

Computation · Statistics 2013-11-12 Selin Damla Ahipasaoglu

Some variant of the Frank-Wolfe method for convex optimization problems with adaptive selection of the step parameter corresponding to information about the smoothness of the objective function (the Lipschitz constant of the gradient).…

Optimization and Control · Mathematics 2023-08-01 G. V. Aivazian , F. S. Stonyakin , D. A. Pasechnyuk , M. S. Alkousa , A. M. Raigorodskii

We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where instead of receiving a numeric reward at each step, the agent only receives preferences over trajectory pairs from a human overseer. The goal of the…

Machine Learning · Computer Science 2022-05-25 Xiaoyu Chen , Han Zhong , Zhuoran Yang , Zhaoran Wang , Liwei Wang

We study a ranking and selection problem of learning from choice-based feedback with dynamic assortments. In this problem, a company sequentially displays a set of items to a population of customers and collects their choices as feedback.…

Machine Learning · Computer Science 2025-01-03 Junwen Yang , Yifan Feng

This paper proposes a new variant of Frank-Wolfe (FW), called $k$FW. Standard FW suffers from slow convergence: iterates often zig-zag as update directions oscillate around extreme points of the constraint set. The new variant, $k$FW,…

Optimization and Control · Mathematics 2021-11-17 Lijun Ding , Jicong Fan , Madeleine Udell

Multi-category support vector machine (MC-SVM) is one of the most popular machine learning algorithms. There are lots of variants of MC-SVM, although different optimization algorithms were developed for different learning machines. In this…

Machine Learning · Computer Science 2021-11-10 Kenya Tajima , Yoshihiro Hirohashi , Esmeraldo Ronnie Rey Zara , Tsuyoshi Kato

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

Machine Learning · Statistics 2026-04-06 Pangpang Liu , Chengchun Shi , Will Wei Sun

The stochastic Frank-Wolfe method has recently attracted much general interest in the context of optimization for statistical and machine learning due to its ability to work with a more general feasible region. However, there has been a…

Optimization and Control · Mathematics 2019-11-06 Haihao Lu , Robert M. Freund

We propose a fast and scalable Polyatomic Frank-Wolfe (P-FW) algorithm for the resolution of high-dimensional LASSO regression problems. The latter improves upon traditional Frank-Wolfe methods by considering generalized greedy steps with…

Signal Processing · Electrical Eng. & Systems 2022-03-03 Adrian Jarret , Julien Fageot , Matthieu Simeoni

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work…

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Machine Learning · Computer Science 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

Recently the away-step Frank-Wolfe algoritm for constrained multiobjective optimization has been shown linear convergence rate over a polytope which is generated by finite points set. In this paper we design a decomposition-invariant…

Optimization and Control · Mathematics 2024-09-10 Zhuoxin Fan , Liping Tang

Aligning large language models (LLM) with human preference plays a key role in building modern generative models and can be achieved by reinforcement learning from human feedback (RLHF). Despite their superior performance, current RLHF…

Machine Learning · Computer Science 2025-02-12 Kaixuan Ji , Jiafan He , Quanquan Gu

Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional preferences, recent studies have explored multi-dimensional…

Machine Learning · Computer Science 2025-06-03 Minhyeon Oh , Seungjoon Lee , Jungseul Ok

Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still limited, particularly when the…

Machine Learning · Computer Science 2024-08-20 Ali Dadras , Sourasekhar Banerjee , Karthik Prakhya , Alp Yurtsever

We propose an enhanced zeroth-order stochastic Frank-Wolfe framework to address constrained finite-sum optimization problems, a structure prevalent in large-scale machine-learning applications. Our method introduces a novel double variance…

Machine Learning · Computer Science 2025-01-24 Haishan Ye , Yinghui Huang , Hao Di , Xiangyu Chang

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Machine Learning · Computer Science 2025-03-04 Branislav Kveton , Xintong Li , Julian McAuley , Ryan Rossi , Jingbo Shang , Junda Wu , Tong Yu

We propose a cost-effective framework for preference elicitation and aggregation under the Plackett-Luce model with features. Given a budget, our framework iteratively computes the most cost-effective elicitation questions in order to help…

Machine Learning · Computer Science 2018-07-10 Zhibing Zhao , Haoming Li , Junming Wang , Jeffrey Kephart , Nicholas Mattei , Hui Su , Lirong Xia
‹ Prev 1 3 4 5 6 7 10 Next ›