English
Related papers

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

200 papers

Data generation and labeling are often expensive in robot learning. Preference-based learning is a concept that enables reliable labeling by querying users with preference questions. Active querying methods are commonly employed in…

Machine Learning · Computer Science 2024-02-27 Erdem Bıyık , Nima Anari , Dorsa Sadigh

This paper explores the adaptive (active) PAC (probably approximately correct) top-$k$ ranking (i.e., top-$k$ item selection) and total ranking problems from $l$-wise ($l\geq 2$) comparisons under the multinomial logit (MNL) model. By…

Machine Learning · Computer Science 2018-09-11 Wenbo Ren , Jia Liu , Ness B. Shroff

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Artificial Intelligence · Computer Science 2025-05-27 Anirudhan Badrinath , Prabhat Agarwal , Jiajing Xu

In this paper, we study optimization methods consisting of iteratively minimizing surrogates of an objective function. By proposing several algorithmic variants and simple convergence analyses, we make two main contributions. First, we…

Machine Learning · Statistics 2013-05-15 Julien Mairal

Model merging has emerged as a promising approach for multi-task learning (MTL), offering a data-efficient alternative to conventional fine-tuning. However, with the rapid development of the open-source AI ecosystem and the increasing…

Machine Learning · Computer Science 2025-10-01 Hao Mark Chen , Shell Xu Hu , Wayne Luk , Timothy Hospedales , Hongxiang Fan

Reinforcement learning with human feedback (RLHF), which learns a reward model from human preference data and then optimizes a policy to favor preferred responses, has emerged as a central paradigm for aligning large language models (LLMs)…

Machine Learning · Statistics 2025-09-29 Gen Li , Yuling Yan

Direct Preference Optimization (DPO) has recently been extended from text-only models to vision-language models. However, existing methods rely on oversimplified pairwise comparisons, generating a single negative image via basic…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Xintong Li , Chuhan Wang , Junda Wu , Rohan Surana , Tong Yu , Julian McAuley , Jingbo Shang

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second,…

Machine Learning · Computer Science 2024-05-01 Joey Hejna , Rafael Rafailov , Harshit Sikchi , Chelsea Finn , Scott Niekum , W. Bradley Knox , Dorsa Sadigh

We present and analyze an away-step Frank-Wolfe method for the convex optimization problem ${\min}_{x\in\mathcal{X}} \; f(\mathsf{A} x) + \langle{c},{x}\rangle$, where $f$ is a $\theta$-logarithmically-homogeneous self-concordant barrier,…

Optimization and Control · Mathematics 2023-08-30 Renbo Zhao

We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback…

Machine Learning · Computer Science 2011-11-04 Pannagadatta K. Shivaswamy , Thorsten Joachims

Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Typically, RLHF involves the initial step of learning a reward model from human feedback,…

This paper analyzes the convergence rates of the {\it Frank-Wolfe } method for solving convex constrained multiobjective optimization. We establish improved convergence rates under different assumptions on the objective function, the…

Optimization and Control · Mathematics 2024-06-11 Douglas S. Gonçalves , Max L. N. Gonçalves , Jefferson G. Melo

Reinforcement Learning from Human Feedback (RLHF) relies on preference modeling to align machine learning systems with human values, yet the popular approach of random pair sampling with Bradley-Terry modeling is statistically limited and…

Human-Computer Interaction · Computer Science 2025-12-02 Andreas Chouliaras , Dimitris Chatzopoulos

We introduce a new projection-free (Frank-Wolfe) method for optimizing structured nonconvex functions that are expressed as a difference of two convex functions. This problem class subsumes smooth nonconvex minimization, positioning our…

Optimization and Control · Mathematics 2025-12-01 Hoomaan Maskan , Yikun Hou , Suvrit Sra , Alp Yurtsever

We consider variants of the classical Frank-Wolfe algorithm for constrained smooth convex minimization, that instead of access to the standard oracle for minimizing a linear function over the feasible set, have access to an oracle that can…

Optimization and Control · Mathematics 2022-02-10 Dan Garber , Noam Wolf

This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw…

Machine Learning · Computer Science 2020-10-22 Sebastian Pokutta , Christoph Spiegel , Max Zimmer

Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be…

Machine Learning · Computer Science 2025-08-20 Jason R Brown , Carl Henrik Ek , Robert D Mullins

We propose a new version of the Frank-Wolfe method, called the (L0, L1)-Frank-Wolfe algorithm, developed for optimization problems with (L0, L1)-smooth objectives. We establish that this algorithm achieves superior theoretical convergence…

Optimization and Control · Mathematics 2026-05-21 A. A. Vyguzov , F. S. Stonyakin

The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps…

Machine Learning · Computer Science 2012-06-22 Elad Hazan , Satyen Kale

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Machine Learning · Computer Science 2025-03-19 Siliang Zeng , Yao Liu , Huzefa Rangwala , George Karypis , Mingyi Hong , Rasool Fakoor