paper-with-me

Papers

A Dimensionality Reduction Method for Finding Least Favorable Priors with a Focus on Bregman Divergence

2022-02-23 · Alex Dytso, Mario Goldenbaum, H. Vincent Poor, Shlomo Shamai

A common way of characterizing minimax estimators in point estimation is by moving the problem into the Bayesian estimation domain and finding a least favorable prior distribution. The Bayesian estimator induced by a least favorable prior, under mild conditions, is then known to be minimax. However, finding least favorable distributions can be challenging due to inherent optimization over the space of probability distributions, which is infinite-dimensional. This paper develops a dimensionality reduction method that allows us to move the optimization to a finite-dimensional setting with an explicit bound on the dimension. The benefit of this dimensionality reduction is that it permits the use of popular algorithms such as projected gradient ascent to find least favorable priors. Throughout the paper, in order to make progress on the problem, we restrict ourselves to Bayesian risks induced by a relatively large class of loss functions, namely Bregman divergences.

📄 PDF Abstract BibTeX arXiv:2202.11598

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality Reduction

Similar Papers 제목 키워드 기반

SCALE SPACE FLOW WITH AUTOREGRESSIVE PRIORS

2021-03-04 · ICLR Workshop Neural_Compression 2021 5 · Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

There has been a recent surge of interest in neural video compression models that combines data-driven dimensionality reduction with learned entropy coding. ScaleSpace Flow (SSF) is among the most popular variants due to…

Dimensionality ReductionOpen-Ended Question AnsweringVideo Compression

Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors

2020-06-14 · NeurIPS 2020 12 · Jorio Cocola, Paul Hand, Vladislav Voroninski

Many problems in statistics and machine learning require the reconstruction of a rank-one signal matrix from noisy data. Enforcing additional prior information on the rank-one component is often key to guaranteeing good …

global-optimization

Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification

2026-06-28 · Zirui Deng, Jingbo Sun, Deyu Meng, Fei Wang arxiv

Repeatedly solving parametric PDEs is essential for uncertainty quantification, design optimization and inverse problems, but conventional neural operators require expensive non-convex training. We introduce PCA--RaNN, a…

Dimensionality Reduction

Exploring the Limits of KV Cache Compression in Visual Autoregressive Transformers

2025-03-19 · Bo Chen, Xiaoyu Li, Yekun Ke, YIngyu Liang 외

A fundamental challenge in Visual Autoregressive models is the substantial memory overhead required during inference to store previously generated representations. Despite various attempts to mitigate this issue through …

Dimensionality Reduction

Simultaneous Dimensionality Reduction: A Data Efficient Approach for Multimodal Representations Learning

2023-10-05 · Eslam Abdelaleem, Ahmed Roman, K. Michael Martini, Ilya Nemenman

We explore two primary classes of approaches to dimensionality reduction (DR): Independent Dimensionality Reduction (IDR) and Simultaneous Dimensionality Reduction (SDR). In IDR methods, of which Principal Components Ana…

Dimensionality Reduction