English
Related papers

Related papers: Direct Distributional Optimization for Provable Al…

200 papers

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Massimiliano Pappa , Luca Collorone , Giovanni Ficarra , Indro Spinelli , Fabio Galasso

Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and therefore should be represented distributionally. In this work,…

Machine Learning · Computer Science 2024-12-31 Hiroki Furuta , Kuang-Huei Lee , Shixiang Shane Gu , Yutaka Matsuo , Aleksandra Faust , Heiga Zen , Izzeddin Gur

In this paper, we explore provable acceleration of diffusion models without any additional retraining. Focusing on the task of approximating a target data distribution in $\mathbb{R}^d$ to within $\varepsilon$ total-variation distance, we…

Machine Learning · Computer Science 2025-08-14 Gen Li , Yuchen Zhou , Yuting Wei , Yuxin Chen

Diffusion models produce high-fidelity speech but are inefficient for real-time use due to long denoising steps and challenges in modeling intonation and rhythm. To improve this, we propose Diffusion Loss-Guided Policy Optimization (DLPO),…

Sound · Computer Science 2025-08-06 Jingyi Chen , Ju Seung Byun , Micha Elsner , Pichao Wang , Andrew Perrault

We propose a Likelihood Matching approach for training diffusion models by first establishing an equivalence between the likelihood of the target data distribution and a likelihood along the sample path of the reverse diffusion. To…

Machine Learning · Statistics 2026-01-23 Lei Qian , Wu Su , Yanqi Huang , Song Xi Chen

We develop a distributed algorithm for convex Empirical Risk Minimization, the problem of minimizing large but finite sum of convex functions over networks. The proposed algorithm is derived from directly discretizing the second-order…

Optimization and Control · Mathematics 2018-11-07 Jingzhao Zhang , César A. Uribe , Aryan Mokhtari , Ali Jadbabaie

Diffusion Schr\"odinger bridges (DSB) have recently emerged as a powerful framework for recovering stochastic dynamics via their marginal observations at different time points. Despite numerous successful applications, existing algorithms…

Distributionally robust optimization (DRO) has been introduced for solving stochastic programs where the distribution of the random parameters is unknown and must be estimated by samples from that distribution. A key element of DRO is the…

Optimization and Control · Mathematics 2019-01-09 Xi Chen , Qihang Lin , Guanglin Xu

This paper introduces a rigorous framework for defining generative diffusion models in infinite dimensions via Doob's h-transform. Rather than relying on time reversal of a noising process, a reference diffusion is forced towards the target…

Machine Learning · Statistics 2026-02-09 Thorben Pieper-Sethmacher , Daniel Paulin

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

Machine Learning · Computer Science 2025-07-22 Junkang Wu , Xue Wang , Zhengyi Yang , Jiancan Wu , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Diffusion models have demonstrated empirical successes in various applications and can be adapted to task-specific needs via guidance. This paper studies a form of gradient guidance for adapting a pre-trained diffusion model towards…

Machine Learning · Statistics 2024-10-17 Yingqing Guo , Hui Yuan , Yukang Yang , Minshuo Chen , Mengdi Wang

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Machine Learning · Statistics 2026-02-03 Yidong Ouyang , Liyan Xie , Hongyuan Zha , Guang Cheng

Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon…

Machine Learning · Computer Science 2026-01-14 Juno Kim , Jihun Yun , Jason D. Lee , Kwang-Sung Jun

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

Diffusion models have attained prominence for their ability to synthesize a probability distribution for a given dataset via a diffusion process, enabling the generation of new data points with high fidelity. However, diffusion processes…

Machine Learning · Computer Science 2024-11-25 Shervin Khalafi , Dongsheng Ding , Alejandro Ribeiro

Recently, there has been a growing interest in distributionally robust optimization (DRO) as a principled approach to data-driven decision making. In this paper, we consider a distributionally robust two-stage stochastic optimization…

Optimization and Control · Mathematics 2020-12-07 Zhe Zhang , Shabbir Ahmed , Guanghui Lan

Optimizing high-dimensional and complex black-box functions is crucial in numerous scientific applications. While Bayesian optimization (BO) is a powerful method for sample-efficient optimization, it struggles with the curse of…

Machine Learning · Computer Science 2025-07-08 Taeyoung Yun , Kiyoung Om , Jaewoo Lee , Sujin Yun , Jinkyoo Park

A novel distributed algorithm is proposed for finite-time converging to a feasible consensus solution satisfying global optimality to a certain accuracy of the distributed robust convex optimization problem (DRCO) subject to bounded…

Optimization and Control · Mathematics 2023-09-06 Xunhao Wu , Jun Fu

Distributionally Robust Optimization (DRO), as a popular method to train robust models against distribution shift between training and test sets, has received tremendous attention in recent years. In this paper, we propose and analyze…

Machine Learning · Computer Science 2023-08-17 Qi Qi , Jiameng Lyu , Kung sik Chan , Er Wei Bai , Tianbao Yang

Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models such as the Bradley-Terry model, this assumption may fail to…