English
Related papers

Related papers: Distributionally Preference Robust Optimization in…

200 papers

In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback…

Information Retrieval · Computer Science 2026-05-04 Xingyu Hu , Kai Zhang , Jiancan Wu , Shuli Wang , Chi Wang , Wenshuai Chen , Yinhua Zhu , Haitao Wang , Xingxing Wang , Xiang Wang

Decision maker's preferences are often captured by some choice functions which are used to rank prospects. In this paper, we consider ambiguity in choice functions over a multi-attribute prospect space. Our main result is a robust…

Risk Management · Quantitative Finance 2018-05-21 William B. Haskell , Wenjie Huang , Huifu Xu

Distributionally robust stochastic optimization (DRSO) is an approach to optimization under uncertainty in which, instead of assuming that there is a known true underlying probability distribution, one hedges against a chosen set of…

Optimization and Control · Mathematics 2022-05-03 Rui Gao , Anton J. Kleywegt

Group distributionally robust optimization (GDRO) aims to develop models that perform well across $m$ distributions simultaneously. Existing GDRO algorithms can only process a fixed number of samples per iteration, either 1 or $m$, and…

Machine Learning · Computer Science 2025-05-22 Haomin Bai , Dingzhi Yu , Shuai Li , Haipeng Luo , Lijun Zhang

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Computation and Language · Computer Science 2025-05-23 Jack Lanchantin , Angelica Chen , Shehzaad Dhuliawala , Ping Yu , Jason Weston , Sainbayar Sukhbaatar , Ilia Kulikov

Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data. Although substantial resources are expended in collecting and labeling datasets, a critical aspect is…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Yunhong Lu , Qichao Wang , Hengyuan Cao , Xiaoyin Xu , Min Zhang

In problems that involve input parameter information gathered from multiple data sources with varying reliability, incorporating decision makers' trust on different sources in optimization models can potentially improve solution…

Optimization and Control · Mathematics 2026-02-27 Yanru Guo , Ruiwei Jiang , Siqian Shen

We propose and analyze a new data-driven trade-off (TRO) approach for modeling uncertainty that serves as a middle ground between the optimistic approach, which adopts a distributional belief, and the pessimistic distributionally robust…

Optimization and Control · Mathematics 2025-01-15 Man Yiu Tsang , Karmel S. Shehadeh

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Machine Learning · Computer Science 2026-01-16 Zaiyan Xu , Sushil Vemuri , Kishan Panaganti , Dileep Kalathil , Rahul Jain , Deepak Ramachandran

We present a novel framework for distributionally robust optimization (DRO), called cost-aware DRO (CADRO). The key idea of CADRO is to exploit the cost structure in the design of the ambiguity set to reduce conservatism. Particularly, the…

Optimization and Control · Mathematics 2023-05-17 Mathijs Schuurmans , Panagiotis Patrinos

To train machine learning models that are robust to distribution shifts in the data, distributionally robust optimization (DRO) has been proven very effective. However, the existing approaches to learning a distributionally robust model…

Machine Learning · Computer Science 2022-03-21 Farzin Haddadpour , Mohammad Mahdi Kamani , Mehrdad Mahdavi , Amin Karbasi

Machine learning systems based on minimizing average error have been shown to perform inconsistently across notable subsets of the data, which is not exposed by a low average error for the entire dataset. In consequential social and…

Machine Learning · Computer Science 2021-06-18 Agnieszka Słowik , Léon Bottou

This paper introduces the distributionally robust random utility model (DRO-RUM), which allows the preference shock (unobserved heterogeneity) distribution to be misspecified or unknown. We make three contributions using tools from the…

Theoretical Economics · Economics 2023-03-13 David Müller , Emerson Melo , Ruben Schlotter

Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation. For example, recent works in DRO have shown that popular statistical estimators can…

Machine Learning · Statistics 2020-04-21 Jose Blanchet , Yang Kang , Fan Zhang , Zhangyi Hu

This paper investigates the joint optimization of condition-based maintenance and spare provisioning, incorporating insights obtained from sensor data. Prognostic models estimate components' remaining lifetime distributions (RLDs), which…

Optimization and Control · Mathematics 2025-07-14 Heraldo Rozas , Weijun Xie , Nagi Gebraeel , Stephen Robinson

In this paper, we consider a network capacity expansion problem in the context of telecommunication networks, where there is uncertainty associated with the expected traffic demand. We employ a distributionally robust stochastic…

Optimization and Control · Mathematics 2020-04-10 Trivikram Dokka , Francis Garuba , Marc Goerigk , Peter Jacko

Quick response is a widely adopted strategy to mitigate overproduction in the manufacturing industry, yet recent research reveals a counter-intuitive paradox: while it reduces waste from unsold finished goods, it may incentivize firms to…

Optimization and Control · Mathematics 2026-02-11 Panayotis P. Papavassilopoulos , Grani A. Hanasusanto , Yijie Wang

Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore…

Machine Learning · Statistics 2020-11-03 Soumyadip Ghosh , Mark Squillante , Ebisa Wollega

We study episodic reinforcement learning (RL) in non-stationary linear kernel Markov decision processes (MDPs). In this setting, both the reward function and the transition kernel are linear with respect to the given feature maps and are…

Machine Learning · Computer Science 2024-12-24 Han Zhong , Zhongren Chen , Zhuoran Yang , Zhaoran Wang , Csaba Szepesvári