English
Related papers

Related papers: Online Posterior Sampling with a Diffusion Prior

200 papers

Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from…

Machine Learning · Computer Science 2025-04-08 Ziyan Wang , Xiaoming Huo , Hao Wang

Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. In this paper, we reveal that recent methods can be uniformly interpreted as employing a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Xinyu Peng , Ziyang Zheng , Wenrui Dai , Nuoqian Xiao , Chenglin Li , Junni Zou , Hongkai Xiong

Gaussian graphical model is one of the powerful tools to analyze conditional independence between two variables for multivariate Gaussian-distributed observations. When the dimension of data is moderate or high, penalized likelihood methods…

Methodology · Statistics 2025-01-24 Takahiro Onizuka , Shintaro Hashimoto

Purpose: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high quality MRI reconstructions with uncertainty estimation from highly undersampled k-space data. However, sampling methods such as…

Medical Physics · Physics 2026-05-26 Moritz Blumenthal , Tina Holliber , Jonathan I. Tamir , Martin Uecker

While contextual bandit has a mature theory, effectively leveraging different feedback patterns to enhance the pace of learning remains unclear. Bandits with feedback graphs, which interpolates between the full information and bandit…

Machine Learning · Computer Science 2023-10-30 Mengxiao Zhang , Yuheng Zhang , Olga Vrousgou , Haipeng Luo , Paul Mineiro

Thompson sampling has proven effective across a wide range of stationary bandit environments. However, as we demonstrate in this paper, it can perform poorly when applied to non-stationary environments. We attribute such failures to the…

Machine Learning · Computer Science 2025-05-06 Yueyang Liu , Xu Kuang , Benjamin Van Roy

We introduce a stochastic contextual bandit model where at each time step the environment chooses a distribution over a context set and samples the context from this distribution. The learner observes only the context distribution while the…

Machine Learning · Statistics 2019-11-15 Johannes Kirschner , Andreas Krause

Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant interest after several studies demonstrated it to have better…

Machine Learning · Computer Science 2014-02-04 Shipra Agrawal , Navin Goyal

Diffusion generative models unlock new possibilities for inverse problems as they allow for the incorporation of strong empirical priors in scientific inference. Recently, diffusion models are repurposed for solving inverse problems using…

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns…

Bayesian neural networks often approximate the weight-posterior with a Gaussian distribution. However, practical posteriors are often, even locally, highly non-Gaussian, and empirical performance deteriorates. We propose a simple parametric…

Machine Learning · Statistics 2023-06-13 Federico Bergamin , Pablo Moreno-Muñoz , Søren Hauberg , Georgios Arvanitidis

Zero-shot diffusion posterior sampling offers a flexible framework for inverse problems by accommodating arbitrary degradation operators at test time, but incurs high computational cost due to repeated likelihood-guided updates. In…

Machine Learning · Statistics 2026-02-10 Léon Zheng , Thomas Hirtz , Yazid Janati , Eric Moulines

Recent advancements in diffusion models have been leveraged to address inverse problems without additional training, and Diffusion Posterior Sampling (DPS) (Chung et al., 2022a) is among the most popular approaches. Previous analyses…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Tongda Xu , Xiyan Cai , Xinjie Zhang , Xingtong Ge , Dailan He , Ming Sun , Jingjing Liu , Ya-Qin Zhang , Jian Li , Yan Wang

Contextual bandits are incredibly useful in many practical problems. We go one step further by devising a more realistic problem that combines: (1) contextual bandits with dense arm features, (2) non-linear reward functions, and (3) a…

Machine Learning · Computer Science 2026-03-18 Wei Min Loh , Sajib Kumer Sinha , Ankur Agarwal , Pascal Poupart

We propose Amortized Posterior Sampling (APS), a novel variational inference approach for efficient posterior sampling in inverse problems. Our method trains a conditional flow model to minimize the divergence between the variational…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Abbas Mammadov , Hyungjin Chung , Jong Chul Ye

Geophysical inverse problems are often ill-posed and admit multiple solutions. Conventional discriminative methods typically yield a single deterministic solution, which fails to model the posterior distribution, cannot generate diverse…

We present the first framework to solve linear inverse problems leveraging pre-trained latent diffusion models. Previously proposed algorithms (such as DPS and DDRM) only apply to pixel-space diffusion models. We theoretically analyze our…

Machine Learning · Computer Science 2023-07-04 Litu Rout , Negin Raoof , Giannis Daras , Constantine Caramanis , Alexandros G. Dimakis , Sanjay Shakkottai

Modern applications routinely collect high-dimensional data, leading to statistical models having more parameters than there are samples available. A common solution is to impose sparsity in parameter estimation, often using penalized…

Methodology · Statistics 2025-07-08 Paolo Onorati , David B. Dunson , Antonio Canale

We propose a novel method for sampling and optimization tasks based on a stochastic interacting particle system. We explain how this method can be used for the following two goals: (i) generating approximate samples from a given target…

Dynamical Systems · Mathematics 2021-11-05 J. A. Carrillo , F. Hoffmann , A. M. Stuart , U. Vaes

We study the problem of using causal models to improve the rate at which good interventions can be learned online in a stochastic environment. Our formalism combines multi-arm bandits and causal inference to model a novel type of bandit…

Machine Learning · Statistics 2016-06-13 Finnian Lattimore , Tor Lattimore , Mark D. Reid