English
Related papers

Related papers: On approximating Gaussian relay networks by determ…

200 papers

Markov networks are frequently used in sciences to represent conditional independence relationships underlying observed variables arising from a complex system. It is often of interest to understand how an underlying network differs between…

Methodology · Statistics 2021-04-26 Byol Kim , Song Liu , Mladen Kolar

In a bi-directional relay channel, a pair of nodes wish to exchange independent messages over a shared wireless half-duplex channel with the help of relays. Recent work has mostly considered information theoretic limits of the…

Information Theory · Computer Science 2010-02-02 Sang Joon Kim , Besma Smida , Natasha Devroye

In this paper, we study the uplink of a cellular system using the linear deterministic approximation model, where there are two users transmitting to a receiver, mutually interfering with a third transmitter communicating with a second…

Information Theory · Computer Science 2011-04-04 J. Buehler , G. Wunder

Diagonal linear networks are neural networks with linear activation and diagonal weight matrices. Their theoretical interest is that their implicit regularization can be rigorously analyzed: from a small initialization, the training of…

Machine Learning · Computer Science 2026-03-19 Raphaël Berthier

In this paper, we derive the information theoretic capacity of a special class of mesh networks. A mesh network is a heterogeneous wireless network in which the transmission among power limited nodes is assisted by powerful relays, which…

Information Theory · Computer Science 2010-04-15 Lawrence Ong , Mehul Motani

We consider the Gaussian interference channel with an intermediate relay as a main building block for cooperative interference networks. On the achievability side, we consider compress-and-forward based strategies. Specifically, a…

Information Theory · Computer Science 2015-03-18 Ye Tian , Aylin Yener

A new communication scheme for Gaussian parallel relay networks based on superposition coding and partial decoding at the relays is presented. Some specific examples are proposed in which two codebook layers are superimposed. The first…

Information Theory · Computer Science 2016-11-18 Farzad Parvaresh , Raul Etkin

In this work, we study bounds on the capacity of full-duplex Gaussian 1-2-1 networks with imperfect beamforming. In particular, different from the ideal 1-2-1 network model introduced in [1], in this model beamforming patterns result in…

Information Theory · Computer Science 2020-05-15 Yahya H. Ezzeldin , Martina Cardone , Christina Fragouli , Giuseppe Caire

The analytic inference, e.g. predictive distribution being in closed form, may be an appealing benefit for machine learning practitioners when they treat wide neural networks as Gaussian process in Bayesian setting. The realistic widths,…

Disordered Systems and Neural Networks · Physics 2023-08-01 Chi-Ken Lu

Many modern distributed systems consist of devices that generate more data than what can be transmitted via a communication link in near real time with high-fidelity. We consider the scheduling problem in which a device has access to…

Systems and Control · Electrical Eng. & Systems 2024-05-20 Marcos M. Vasconcelos , Yifei Zhang

Deep generative networks can simulate from a complex target distribution, by minimizing a loss with respect to samples from that distribution. However, often we do not have direct access to our target distribution - our data may be subject…

An analytically tractable model for Gaussian multiuser channels with fading is studied, and the capacity region of this model is found to be a good approximation of the capacity region of the original Gaussian network. This work extends the…

Information Theory · Computer Science 2009-05-16 Rony EL Haddad , Brian Smith , Sriram Vishwanath

The capacity of a network in which a multiple access channel (MAC) generates interference to a single-user channel is studied. An achievable rate region based on superposition coding and joint decoding is established for the discrete case.…

Information Theory · Computer Science 2012-09-06 Fangfang Zhu , Xiaohu Shang , Biao Chen , H. Vincent Poor

An information measure based on fractional partitions of a set is used to derive a general dependence balance inequality for communication. This inequality is used to obtain new upper bounds on reliable and secret rates for multiterminal…

Information Theory · Computer Science 2026-04-14 Amin Gohari , Gerhard Kramer

Despite exceptional predictive performance of Deep sequence models (DSMs), the main concern of their deployment centers around the lack of uncertainty awareness. In contrast, probabilistic models quantify the uncertainty associated with…

Machine Learning · Computer Science 2026-03-03 Wenlong Chen

Recently there has been a lot of success in using the deterministic approach to provide approximate characterization of Gaussian network capacity. In this paper, we take a deterministic view and revisit the problem of wiretap channel with…

Information Theory · Computer Science 2016-11-17 Mustafa El-Halabi , Tie Liu , Costas Georghiades , Shlomo Shamai

Uplink-downlink duality refers to the fact that under a sum-power constraint, the capacity regions of a Gaussian multiple-access channel and a Gaussian broadcast channel with Hermitian transposed channel matrices are identical. This paper…

Information Theory · Computer Science 2021-08-27 Liang Liu , Ya-Feng Liu , Pratik Patil , Wei Yu

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

Probability · Mathematics 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control. Inspired by recent work establishing links between residual networks and control systems, we provide a…

Machine Learning · Computer Science 2024-02-12 Paulo Tabuada , Bahman Gharesifard

Gaussian processes retain the linear model either as a special case, or in the limit. We show how this relationship can be exploited when the data are at least partially linear. However from the perspective of the Bayesian posterior, the…

Methodology · Statistics 2008-07-13 Robert B. Gramacy , Herbert K. H. Lee