English
Related papers

Related papers: The Offline-Frontier Shift: Diagnosing Distributio…

200 papers

Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-used joint training strategy, which has a uniform objective…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Yake Wei , Di Hu , Henghui Du , Ji-Rong Wen

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…

Machine Learning · Computer Science 2025-08-04 David McAllister , Songwei Ge , Brent Yi , Chung Min Kim , Ethan Weber , Hongsuk Choi , Haiwen Feng , Angjoo Kanazawa

Data analytics in the cloud has become an integral part of enterprise businesses. Big data analytics systems, however, still lack the ability to take user performance goals and budgetary constraints for a task, collectively referred to as…

Databases · Computer Science 2020-05-08 Fei Song , Khaled Zaouk , Chenghao Lyu , Arnab Sinha , Qi Fan , Yanlei Diao , Prashant Shenoy

Inverse design problems are common in engineering and materials science. The forward direction, i.e., computing output quantities from design parameters, typically requires running a numerical simulation, such as a FEM, as an intermediate…

Machine Learning · Computer Science 2026-02-18 Jens U. Kreber , Christian Weißenfels , Joerg Stueckler

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Machine Learning · Computer Science 2024-05-31 Zeyu Fang , Tian Lan

We study sequential decision-making with offline reinforcement learning (RL). Traditional offline RL policies may result in out-of-distribution (OOD) actions when training relies only on sparse offline representations. To ensure safe…

Machine Learning · Computer Science 2026-05-26 Aysin Tumay , Jiahe Huang , Elise Jortberg , Rose Yu

Optimizing the performance of many objectives (instantiated by tasks or clients) jointly with a few Pareto stationary solutions (models) is critical in machine learning. However, previous multi-objective optimization methods often focus on…

Machine Learning · Computer Science 2024-03-08 Ziyue Li , Tian Li , Virginia Smith , Jeff Bilmes , Tianyi Zhou

The objective of offline RL is to learn optimal policies when a fixed exploratory demonstrations data-set is available and sampling additional observations is impossible (typically if this operation is either costly or rises ethical…

Machine Learning · Computer Science 2021-06-10 Firas Jarboui , Vianney Perchet

Online alignment (e.g., GRPO) is generally more performant than offline alignment (e.g., DPO) -- but why? Drawing on prospect theory from behavioral economics, we propose a human-centric explanation. We prove that online on-policy sampling…

Artificial Intelligence · Computer Science 2026-03-30 Sijia Liu , Niklas Muennighoff , Kawin Ethayarajh

The rapid expansion of edge devices and Internet-of-Things (IoT) continues to heighten the demand for data transport under limited spectrum resources. The goal-oriented communications (GO-COM), unlike traditional communication systems…

Image and Video Processing · Electrical Eng. & Systems 2025-10-07 Suchinthaka Wanninayaka , Achintha Wijesinghe , Weiwei Wang , Yu-Chieh Chao , Songyang Zhang , Zhi Ding

3D Mixed Reality interfaces have nearly unlimited space for layout placement, making automatic UI adaptation crucial for enhancing the user experience. Such adaptation is often formulated as a multi-objective optimization (MOO) problem,…

Human-Computer Interaction · Computer Science 2025-09-24 Yao Song , Christoph Gebhardt , Yi-Chi Liao , Christian Holz

Recent advancements in the realm of deep generative models focus on generating samples that satisfy multiple desired properties. However, prevalent approaches optimize these property functions independently, thus omitting the trade-offs…

Machine Learning · Computer Science 2024-07-08 Yinghua Yao , Yuangang Pan , Jing Li , Ivor Tsang , Xin Yao

Online feedback optimization (OFO) enables optimal steady-state operations of a physical system by employing an iterative optimization algorithm as a dynamic feedback controller. When the plant consists of several interconnected…

Optimization and Control · Mathematics 2024-09-13 Wenbin Wang , Zhiyu He , Giuseppe Belgioioso , Saverio Bolognani , Florian Dörfler

For the purpose of addressing the multi-objective optimal reactive power dispatch (MORPD) problem, a two-step approach is proposed in this paper. First of all, to ensure the economy and security of the power system, the MORPD model aiming…

Optimization and Control · Mathematics 2020-03-06 Meng Zhang , Yang Li

Motivated by energy management for micro-grids, we study convex optimization problems with uncertainty in the objective function and sequential decision making. To solve these problems, we propose a new framework called ``Online…

Optimization and Control · Mathematics 2020-08-25 Martijn H. H. Schoot Uiterkamp , Marco E. T. Gerards , Johann L. Hurink

In the field of evolutionary multi-objective optimization, the approximation of the Pareto front (PF) is achieved by utilizing a collection of representative candidate solutions that exhibit desirable convergence and diversity. Although…

Neural and Evolutionary Computing · Computer Science 2024-07-10 Peng Chen , Jing Liang , Kangjia Qiao , Ponnuthurai Nagaratnam Suganthan , Xuanxuan Ban

This paper focuses on wireless multiple-input multiple-output (MIMO)-orthogonal frequency division multiplex (OFDM) receivers. Traditional wireless receivers have relied on mathematical modeling and Bayesian inference, achieving remarkable…

Signal Processing · Electrical Eng. & Systems 2026-01-30 Yuzhi Yang , Omar Alhussein , Atefeh Arani , Zhaoyang Zhang , Mérouane Debbah

Offline reinforcement learning seeks to utilize offline (observational) data to guide the learning of (causal) sequential decision making strategies. The hope is that offline reinforcement learning coupled with function approximation…

Machine Learning · Computer Science 2020-10-23 Ruosong Wang , Dean P. Foster , Sham M. Kakade

Efficiently solving multi-objective optimization problems for simulation optimization of important scientific and engineering applications such as materials design is becoming an increasingly important research topic. This is due largely to…

Artificial Intelligence · Computer Science 2023-06-27 Eric Hans Lee , Bolong Cheng , Michael McCourt

The task of predicting human motion is complicated by the natural heterogeneity and compositionality of actions, necessitating robustness to distributional shifts as far as out-of-distribution (OoD). Here we formulate a new OoD benchmark…

Computer Vision and Pattern Recognition · Computer Science 2020-11-26 Anthony Bourached , Ryan-Rhys Griffiths , Robert Gray , Ashwani Jha , Parashkev Nachev
‹ Prev 1 4 5 6 7 8 10 Next ›