English
Related papers

Related papers: Exact Reformulation and Optimization for Direct Me…

200 papers

Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional objectives or constraints in the policy optimization step.…

Ranking methods or models based on their performance is of prime importance but is tricky because performance is fundamentally multidimensional. In the case of classification, precision and recall are scores with probabilistic…

Performance · Computer Science 2026-03-31 Sébastien Piérard , Adrien Deliège , Marc Van Droogenbroeck

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

Fine-tuning is integral for aligning large language models (LLMs) with human preferences. Multiple-Reference Preference Optimization (MRPO) builds on Direct Preference Optimization (DPO) by fine-tuning LLMs on preference datasets while…

Machine Learning · Computer Science 2025-12-12 Skyler Wu , Aymen Echarghaoui

Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare. While numerous studies have explored…

Machine Learning · Computer Science 2025-09-10 Ali Nawaz , Amir Ahmad , Shehroz S. Khan

Robust Optimal Control (ROC) with adjustable uncertainties has proven to be effective in addressing critical challenges within modern energy networks, especially the reserve and provision problem. However, prior research on ROC with…

Systems and Control · Electrical Eng. & Systems 2023-12-19 Yun Li , Neil Yorke-Smith , Tamas Keviczky

Binary classification involves predicting the label of an instance based on whether the model score for the positive class exceeds a threshold chosen based on the application requirements (e.g., maximizing recall for a precision bound).…

Machine Learning · Computer Science 2023-11-21 Gundeep Arora , Srujana Merugu , Anoop Saladi , Rajeev Rastogi

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

DPO is an effective preference optimization algorithm. However, the DPO-tuned models tend to overfit on the dispreferred samples, manifested as overly long generations lacking diversity. While recent regularization approaches have…

Computation and Language · Computer Science 2025-08-26 Chenxu Yang , Ruipeng Jia , Naibin Gu , Zheng Lin , Siyuan Chen , Chao Pang , Weichong Yin , Yu Sun , Hua Wu , Weiping Wang

Incremental Learning (IL) trains models sequentially on new data without full retraining, offering privacy, efficiency, and scalability. IL must balance adaptability to new data with retention of old knowledge. However, evaluations often…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Matthias Neuwirth-Trapp , Maarten Bieshaar , Danda Pani Paudel , Luc Van Gool

Distributionally robust optimal control (DROC) is gaining interest. This study presents a reformulation method for discrete DROC (DDROC) problems to design optimal control policies under a worst-case distributional uncertainty. The…

Optimization and Control · Mathematics 2025-10-22 Yuma Shida , Yuji Ito

Supervised fine-tuning (SFT) is the standard approach for binary classification tasks such as toxicity detection, factuality verification, and causal inference. However, SFT often performs poorly in real-world settings with label noise,…

Machine Learning · Computer Science 2026-02-04 Punya Syon Pandey , Zhijing Jin

Real-world classification domains, such as medicine, health and safety, and finance, often exhibit imbalanced class priors and have asynchronous misclassification costs. In such cases, the classification model must achieve a high recall…

Machine Learning · Computer Science 2021-05-11 Michał Koziarski , Colin Bellinger , Michał Woźniak

Many existing group fairness-aware training methods aim to achieve the group fairness by either re-weighting underrepresented groups based on certain rules or using weakly approximated surrogates for the fairness metrics in the objective as…

Machine Learning · Computer Science 2023-03-02 Sangwon Jung , Taeeon Park , Sanghyuk Chun , Taesup Moon

Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human preferences. These algorithms implicitly treat the LLM as a reward…

Computation and Language · Computer Science 2025-07-29 Tong Liu , Xiao Yu , Wenxuan Zhou , Jindong Gu , Volker Tresp

Selecting an appropriate evaluation metric for classifiers is crucial for model comparison, parameter optimization, and deployment decisions, yet there is no consensus on a broadly accepted evaluation paradigm explicitly aligned with Total…

Machine Learning · Computer Science 2026-05-28 Pierangelo Lombardo , Antonio Casoli , Cristian Cingolani , Shola Oshodi , Michele Zanatta

Areas under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for evaluating classification performance for imbalanced problems. Compared with AUROC, AUPRC is a more appropriate metric for highly imbalanced datasets. While…

Machine Learning · Computer Science 2023-04-14 Qi Qi , Youzhi Luo , Zhao Xu , Shuiwang Ji , Tianbao Yang

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the…

Machine Learning · Computer Science 2019-02-05 Dahyun Kim , Jihwan Bae , Yeonsik Jo , Jonghyun Choi

We propose a technique for reformulation of state and parameter estimation problems as that of matching explicitly computable definite integrals with known kernels to data. The technique applies for a class of systems of nonlinear ordinary…

Optimization and Control · Mathematics 2013-09-11 I. Yu. Tyukin , A. N. Gorban

Machine learning models deployed in real-world applications are often evaluated with precision-based metrics such as F1-score or AUC-PR (Area Under the Curve of Precision Recall). Heavily dependent on the class prior, such metrics make it…

Machine Learning · Computer Science 2020-04-29 Wissam Siblini , Jordan Fréry , Liyun He-Guelton , Frédéric Oblé , Yi-Qing Wang