paper-with-me

Papers

Learning Rate Free Sampling in Constrained Domains

2023-05-24 · Louis Sharrock, Lester Mackey, Christopher Nemeth

We introduce a suite of new particle-based algorithms for sampling in constrained domains which are entirely learning rate free. Our approach leverages coin betting ideas from convex optimisation, and the viewpoint of constrained sampling as a mirrored optimisation problem on the space of probability measures. Based on this viewpoint, we also introduce a unifying framework for several existing constrained sampling algorithms, including mirrored Langevin dynamics and mirrored Stein variational gradient descent. We demonstrate the performance of our algorithms on a range of numerical examples, including sampling from targets on the simplex, sampling with fairness constraints, and constrained sampling problems in post-selection inference. Our results indicate that our algorithms achieve competitive performance with existing constrained sampling methods, without the need to tune any hyperparameters.

📄 PDF Abstract BibTeX arXiv:2305.14943

Code (1)

louissharrock/constrained-coin-sampling 공식 구현

Tasks

Fairness

Similar Papers 제목 키워드 기반

Learning Rate Free Bayesian Inference in Constrained Domains

2023-09-21 · NeurIPS 2023 11

We introduce a suite of new particle-based algorithms for sampling on constrained domains which are entirely learning rate free. Our approach leverages coin betting ideas from convex optimisation, and the viewpoint of co…

Sampling constrained probability distributions using Spherical Augmentation

2015-06-19 · Shiwei Lan, Babak Shahbaba

Statistical models with constrained probability distributions are abundant in machine learning. Some examples include regression models with norm constraints (e.g., Lasso), probit, many copula models, and latent Dirichle…

Bayesian Inferenceregression

Improved Constrained Generation by Bridging Pretrained Generative Models

2026-03-06 · Xiaoxuan Liang, Saeid Naderiparizi, Yunpeng Liu, Berend Zwartsenberg 외 arxiv

Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constr…

Autonomous Driving

Constrained Diffusion with Trust Sampling

2024-11-17 · William Huang, Yifeng Jiang, Tom Van Wouwe, C. Karen Liu

Diffusion models have demonstrated significant promise in various generative tasks; however, they often struggle to satisfy challenging constraints. Our approach addresses this limitation by rethinking training-free loss…

Motion Generation

Constrained Reinforcement Learning with Average Reward Objective: Model-Based and Model-Free Algorithms

2024-06-17 · Vaneet Aggarwal, Washim Uddin Mondal, Qinbo Bai

Reinforcement Learning (RL) serves as a versatile framework for sequential decision-making, finding applications across diverse domains such as robotics, autonomous driving, recommendation systems, supply chain optimizat…

Autonomous DrivingDecision MakingmodelRecommendation Systems+2