English
Related papers

Related papers: Generalized Statistics Framework for Rate Distorti…

200 papers

Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational distribution and minimizes its KL divergence to the posterior.…

Machine Learning · Statistics 2020-01-29 Robert Bamler , Cheng Zhang , Manfred Opper , Stephan Mandt

3D Gaussian Splatting (3DGS) has become an emerging technique with remarkable potential in 3D representation and image rendering. However, the substantial storage overhead of 3DGS significantly impedes its practical applications. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Henan Wang , Hanxin Zhu , Tianyu He , Runsen Feng , Jiajun Deng , Jiang Bian , Zhibo Chen

Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be made more efficient by partitioning the process across multiple devices, which, in turn,…

Machine Learning · Computer Science 2026-04-21 Anderson de Andrade , Alon Harell , Ivan V. Bajić

This PhD Thesis presents an investigation into the analysis of financial returns using mixture models, focusing on mixtures of generalized normal distributions (MGND) and their extensions. The study addresses several critical issues…

Statistical Finance · Quantitative Finance 2024-11-20 Pierdomenico Duttilo

This paper is concerned with quantum data compression of asymptotically many independent and identically distributed copies of ensembles of mixed quantum states. The encoder has access to a side information system. The figure of merit is…

Quantum Physics · Physics 2024-06-21 Zahra Baghali Khanian , Kohdai Kuroiwa , Debbie Leung

Excessive computational cost for learning large data and streaming data can be alleviated by using stochastic algorithms, such as stochastic gradient descent and its variants. Recent advances improve stochastic algorithms on convergence…

Machine Learning · Statistics 2019-09-24 Shih-Kang Chao , Guang Cheng

We show that the maximum expected inner product between a random vector and the standard normal vector over all couplings subject to a mutual information constraint or regularization is equivalent to a truncated integral involving the…

Information Theory · Computer Science 2026-04-16 Jingbo Liu

Deep generative models (DGMs) are data-eager because learning a complex model on limited data suffers from a large variance and easily overfits. Inspired by the classical perspective of the bias-variance tradeoff, we propose regularized…

Machine Learning · Computer Science 2023-04-11 Yong Zhong , Hongtao Liu , Xiaodong Liu , Fan Bao , Weiran Shen , Chongxuan Li

Graph-based methods provide a powerful tool set for many non-parametric frameworks in Machine Learning. In general, the memory and computational complexity of these methods is quadratic in the number of examples in the data which makes them…

Machine Learning · Computer Science 2013-09-27 Saeed Amizadeh , Bo Thiesson , Milos Hauskrecht

Recent advances have significantly improved our understanding of the generalization performance of gradient descent (GD) methods in deep neural networks. A natural and fundamental question is whether GD can achieve generalization rates…

Machine Learning · Computer Science 2026-04-14 Yuanfan Li , Yunwen Lei , Zheng-Chu Guo , Yiming Ying

The rate-distortion function (RDF) has long been an information-theoretic benchmark for data compression. As its natural extension, the indirect rate-distortion function (iRDF) corresponds to the scenario where the encoder can only access…

Information Theory · Computer Science 2025-03-11 Zichao Yu , Qiang Sun , Wenyi Zhang

Several emerging post-Bayesian methods target a probability distribution for which an entropy-regularised variational objective is minimised. This increased flexibility introduces a computational challenge, as one loses access to an…

Computation · Statistics 2025-12-17 Clémentine Chazal , Heishiro Kanagawa , Zheyang Shen , Anna Korba , Chris. J. Oates

We consider distributed learning using constant stepsize SGD (DSGD) over several devices, each sending a final model update to a central server. In a final step, the local estimates are aggregated. We prove in the setting of…

Machine Learning · Statistics 2022-10-24 Mike Nguyen , Charly Kirst , Nicole Mücke

Introducing the generalized, non-extensive statistics proposed by Tsallis[1988], into the standard s-wave pairing BCS theory of superconductivity in 2D yields a reasonable description of many of the main properties of high temperature…

Superconductivity · Physics 2009-11-07 H. Uys , H. G. Miller , F. C. Khanna

The Blahut-Arimoto (BA) algorithm has played a fundamental role in the numerical computation of rate-distortion (RD) functions. This algorithm possesses a desirable monotonic convergence property by alternatively minimizing its Lagrangian…

Information Theory · Computer Science 2024-01-19 Lingyi Chen , Shitong Wu , Wenhao Ye , Huihui Wu , Wenyi Zhang , Hao Wu , Bo Bai

We study the application of the Augmented Lagrangian Method to the solution of linear ill-posed problems. Previously, linear convergence rates with respect to the Bregman distance have been derived under the classical assumption of a…

Numerical Analysis · Mathematics 2015-06-04 Klaus Frick , Markus Grasmair

The rate-distortion saddle-point problem considered by Lapidoth (1997) consists in finding the minimum rate to compress an arbitrary ergodic source when one is constrained to use a random Gaussian codebook and minimum (Euclidean) distance…

Information Theory · Computer Science 2018-09-03 Lin Zhou , Vincent Y. F. Tan , Mehul Motani

We introduce an alternative closed form lower bound on the Gaussian process ($\mathcal{GP}$) likelihood based on the R\'enyi $\alpha$-divergence. This new lower bound can be viewed as a convex combination of the Nystr\"om approximation and…

Machine Learning · Statistics 2023-07-04 Xubo Yue , Raed Kontar

We derive a simple general parametric representation of the rate-distortion function of a memoryless source, where both the rate and the distortion are given by integrals whose integrands include the minimum mean square error (MMSE) of the…

Information Theory · Computer Science 2010-04-30 Neri Merhav

Algorithms based on multiple decoding attempts of Reed-Solomon (RS) codes have recently attracted new attention. Choosing decoding candidates based on rate-distortion (R-D) theory, as proposed previously by the authors, currently provides…

Information Theory · Computer Science 2016-11-17 Phong S. Nguyen , Henry D. Pfister , Krishna R. Narayanan