English
Related papers

Related papers: Phase Transitions in Rate Distortion Theory and De…

200 papers

In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization. Previous CNN quantization techniques tend to ignore the joint statistics of weights and activations, producing sub-optimal CNN…

Computer Vision and Pattern Recognition · Computer Science 2021-11-09 Sean I. Young , Wang Zhe , David Taubman , Bernd Girod

Recent insights have revealed that rate-coding is a primary form of information representation captured by surrogate-gradient-based Backpropagation Through Time (BPTT) in training deep Spiking Neural Networks (SNNs). Motivated by these…

Machine Learning · Computer Science 2024-10-23 Chengting Yu , Lei Liu , Gaoang Wang , Erping Li , Aili Wang

Contemporary lossy image and video coding standards rely on transform coding, the process through which pixels are mapped to an alternative representation to facilitate efficient data compression. Despite impressive performance of…

Image and Video Processing · Electrical Eng. & Systems 2023-02-21 Lyndon R. Duong , Bohan Li , Cheng Chen , Jingning Han

Studies have been made on the phase transition phenomena of an oscillator network model based on a standard Hebb learning rule like the Hopfield model. The relative phase informations---the in-phase and anti-phase, can be embedded in the…

Disordered Systems and Neural Networks · Physics 2014-09-08 Toru Aonishi

The past several years have witnessed a surge of research investigating various aspects of sparse representations and compressed sensing. Most of this work has focused on the finite-dimensional setting in which the goal is to decompose a…

Information Theory · Computer Science 2016-11-17 Yonina C. Eldar

Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models. Fitting these models by maximizing the marginal likelihood or evidence is typically intractable, thus a common approximation…

Machine Learning · Computer Science 2018-02-15 Alexander A. Alemi , Ben Poole , Ian Fischer , Joshua V. Dillon , Rif A. Saurous , Kevin Murphy

We propose a flexible convex relaxation for the phase retrieval problem that operates in the natural domain of the signal. Therefore, we avoid the prohibitive computational cost associated with "lifting" and semidefinite programming (SDP)…

Information Theory · Computer Science 2017-03-17 Sohail Bahmani , Justin Romberg

The rate-distortion dimension (RDD) of an analog stationary process is studied as a measure of complexity that captures the amount of information contained in the process. It is shown that the RDD of a process, defined as two times the…

Information Theory · Computer Science 2016-11-18 Farideh Ebrahim Rezagah , Shirin Jalali , Elza Erkip , H. Vincent Poor

We establish the first information-theoretic limits for multimodal retrieval. Casting ranking as lossy source coding, we derive a single-letter rate-distortion function $R(D)$ for reciprocal-rank distortion and prove a converse bound that…

Information Theory · Computer Science 2025-09-16 Thomas Y. Chen

We study the rate-distortion problem for both scalar and vector memoryless heavy-tailed $\alpha$-stable sources ($0 < \alpha < 2$). Using a recently defined notion of ``strength" as a power measure, we derive the rate-distortion function…

Information Theory · Computer Science 2026-02-27 Karim Ezzeddine , Jihad Fahs , Ibrahim Abou-Faycal

Scalar quantization is the most practical and straightforward approach to signal quantization. However, it has been shown that scalar quantization of oversampled or Compressively Sensed signals can be inefficient in terms of the…

Information Theory · Computer Science 2011-07-18 Petros T. Boufounos

We improve the existing achievable rate regions for causal and for zero-delay source coding of stationary Gaussian sources under an average mean squared error (MSE) distortion measure. To begin with, we find a closed-form expression for the…

Information Theory · Computer Science 2011-05-03 Milan S. Derpich , Jan Østergaard

Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant…

Computer Vision and Pattern Recognition · Computer Science 2018-02-09 David Minnen , George Toderici , Michele Covell , Troy Chinen , Nick Johnston , Joel Shor , Sung Jin Hwang , Damien Vincent , Saurabh Singh

We derive quantum counterparts of two key theorems of classical information theory, namely, the rate distortion theorem and the source-channel separation theorem. The rate-distortion theorem gives the ultimate limits on lossy data…

Quantum Physics · Physics 2012-12-21 Nilanjana Datta , Min-Hsiu Hsieh , Mark M. Wilde

We give a broad generalisation of the mapping, originally due to Dennis, Kitaev, Landahl and Preskill, from quantum error correcting codes to statistical mechanical models. We show how the mapping can be extended to arbitrary stabiliser or…

Quantum Physics · Physics 2021-06-03 Christopher T. Chubb , Steven T. Flammia

Neural networks acquire structured representations at specific moments during training, yet identifying these transitions typically relies on retrospective, label-dependent metrics. We introduce a bifurcation theory of representation…

Machine Learning · Computer Science 2026-05-26 Fuming Yang

We study the compressed sensing reconstruction problem for a broad class of random, band-diagonal sensing matrices. This construction is inspired by the idea of spatial coupling in coding theory. As demonstrated heuristically and…

Information Theory · Computer Science 2015-03-19 David L. Donoho , Adel Javanmard , Andrea Montanari

We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…

Machine Learning · Computer Science 2024-03-15 Vladimir R. Kostic , Pietro Novelli , Riccardo Grazzi , Karim Lounici , Massimiliano Pontil

The large scale behavior of systems having a large number of interacting degrees of freedom is suitably described using renormalization group, from non-Gaussian distributions. Renormalization group techniques used in physics are then…

High Energy Physics - Theory · Physics 2022-03-04 Vincent Lahoche , Dine Ousmane Samary , Mohamed Tamaazousti

This paper explores the problem of learning transforms for image compression via autoencoders. Usually, the rate-distortion performances of image compression are tuned by varying the quantization step size. In the case of autoen-coders,…

Image and Video Processing · Electrical Eng. & Systems 2018-02-27 Thierry Dumas , Aline Roumy , Christine Guillemot