paper-with-me

홈 › Papers

Half-Space and Box Constraints as NUV Priors: First Results

2021-08-31 · Raphael Keusch, Hans-Andrea Loeliger

Normals with unknown variance (NUV) can represent many useful priors and blend well with Gaussian models and message passing algorithms. NUV representations of sparsifying priors have long been known, and NUV representations of binary (and M-level) priors have been proposed very recently. In this document, we propose NUV representations of half-space constraints and box constraints, which allows to add such constraints to any linear Gaussian model with any of the previously known NUV priors without affecting the computational tractability.

📄 PDF Abstract BibTeX arXiv:2109.00036

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Symbol Guided Hindsight Priors for Reward Learning from Human Preferences

2022-10-17 · Mudit Verma, Katherine Metcalf

Specifying rewards for reinforcement learned (RL) agents is challenging. Preference-based RL (PbRL) mitigates these challenges by inferring a reward from feedback over sets of trajectories. However, the effectiveness of …

Normalizing Flows with Multi-Scale Autoregressive Priors

2020-04-08 · CVPR 2020 6 · Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz, Bernt Schiele 외

Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis. Owing to the efficiency constraints on the design of the flow layers, e.g. sp…

Density EstimationImage Generation

SP$^3$: Spherical Priors for Plug-and-Play Restoration

2026-06-15 · Sean Man, Ron Raphaeli, Matan Kleiner, Or Ronai arxiv

In this paper, we introduce SP$^3$, a novel Plug-and-Play algorithm that accelerates maximum a posteriori image restoration by replacing denoisers with Spherical Encoders (SE) as generative priors. SP$^3$ approximates th…

Image Restoration

Private Learning of Halfspaces: Simplifying the Construction and Reducing the Sample Complexity

2020-04-16 · NeurIPS 2020 12 · Haim Kaplan, Yishay Mansour, Uri Stemmer, Eliad Tsfadia

We present a differentially private learner for halfspaces over a finite grid $G$ in $\mathbb{R}^d$ with sample complexity $\approx d^{2.5}\cdot 2^{\log^*|G|}$, which improves the state-of-the-art result of [Beimel et al…

Improved Hardness Results for Learning Intersections of Halfspaces

2024-02-25 · Stefan Tiegel

We show strong (and surprisingly simple) lower bounds for weakly learning intersections of halfspaces in the improper setting. Strikingly little is known about this problem. For instance, it is not even known if there is…