arXiv subjects

Shitong Wu

Publications and source records attributed to Shitong Wu.

17 recordsLinked to original sources

arXiv2026

A Survey of Learn-to-Compute Paradigms for Rate-Distortion-Type Problems

Rate-distortion (RD) theory and its related formulations play a central role in understanding efficient information representation, but computing these quantities remains challenging in high-dimensional settings. Classical iterative methods such as the Blahut-Arimoto algorithm become impractical in high-dimensional domains due to the curse of dimensionality and the intractability of mutual-information terms. Recent advances in neural modeling and differentiable optimization offer a promising alternative through a learn-to-compute paradigm, in which probability distributions and objective functionals are represented by flexible neural parameterizations. This survey presents an overview of neural approaches for evaluating the RD-type objectives. We present three representative families of methods: variational inference, neural mutual-information estimation, and dual-form optimization. By reviewing their theoretical principles, algorithmic techniques, and consistency properties, we elucidate how these methods collectively transform classical RD-type problems into scalable differentiable objectives suitable for deep learning, though challenges remain in large-scale applications. Together, these perspectives offer promising avenues for scaling information-theoretic computation to complex, high-dimensional machine learning systems.

cs.IT↗

arXiv2025

An Optimal Transport-Based Method for Computing LM Rate and Its Convergence Analysis

The mismatch capacity characterizes the highest information rate of the channel under a prescribed decoding metric and serves as a critical performance indicator in numerous practical communication scenarios. Compared to the commonly used Generalized Mutual Information (GMI), the Lower bound on the Mismatch capacity (LM rate) generally provides a tighter lower bound on the mismatch capacity. However, the efficient computation of the LM rate is significantly more challenging than that of the GMI, particularly as the size of the channel input alphabet increases. This growth in complexity renders standard numerical methods (e.g., interior point methods) computationally intensive and, in some cases, impractical. In this work, we reformulate the computation of the LM rate as a special instance of the optimal transport (OT) problem with an additional constraint. Building on this formulation, we develop a novel numerical algorithm based on the Sinkhorn algorithm, which is well known for its efficiency in solving entropy regularized optimization problems. We further provide the convergence analysis of the proposed algorithm, revealing that the algorithm has a sub-linear convergence rate. Numerical experiments demonstrate the feasibility and efficiency of the proposed algorithm for the computation of the LM rate.

cs.IT↗

arXiv2025

Efficient Computation of Marton's Error Exponent via Constraint Decoupling

The error exponent in lossy source coding characterizes the asymptotic decay rate of error probability with respect to blocklength. The Marton's error exponent provides the theoretically optimal bound on this rate. However, computation methods of the Marton's error exponent remain underdeveloped due to its formulation as a non-convex optimization problem with limited efficient solvers. While a recent grid search algorithm can compute its inverse function, it incurs prohibitive computational costs from two-dimensional brute-force parameter grid searches. This paper proposes a composite maximization approach that effectively handles both Marton's error exponent and its inverse function. Through a constraint decoupling technique, the resulting problem formulations admit efficient solvers driven by an alternating maximization algorithm. By fixing one parameter via a one-dimensional line search, the remaining subproblem becomes convex and can be efficiently solved by alternating variable updates, thereby significantly reducing search complexity. Therefore, the global convergence of the algorithm can be guaranteed. Numerical experiments for simple sources and the Ahlswede's counterexample, demonstrates the superior efficiency of our algorithm in contrast to existing methods.

cs.IT↗

arXiv2025

Neural Estimation of the Information Bottleneck Based on a Mapping Approach

The information bottleneck (IB) method is a technique designed to extract meaningful information related to one random variable from another random variable, and has found extensive applications in machine learning problems. In this paper, neural network based estimation of the IB problem solution is studied, through the lens of a novel formulation of the IB problem. Via exploiting the inherent structure of the IB functional and leveraging the mapping approach, the proposed formulation of the IB problem involves only a single variable to be optimized, and subsequently is readily amenable to data-driven estimators based on neural networks. A theoretical analysis is conducted to guarantee that the neural estimator asymptotically solves the IB problem, and the numerical experiments on both synthetic and MNIST datasets demonstrate the effectiveness of the neural estimator.

cs.IT↗

arXiv2025

Estimating Rate-Distortion Functions Using the Energy-Based Model

The rate-distortion (RD) theory is one of the key concepts in information theory, providing theoretical limits for compression performance and guiding the source coding design, with both theoretical and practical significance. The Blahut-Arimoto (BA) algorithm, as a classical algorithm to compute RD functions, encounters computational challenges when applied to high-dimensional scenarios. In recent years, many neural methods have attempted to compute high-dimensional RD problems from the perspective of implicit generative models. Nevertheless, these approaches often neglect the reconstruction of the optimal conditional distribution or rely on unreasonable prior assumptions. In face of these issues, we propose an innovative energy-based modeling framework that leverages the connection between the RD dual form and the free energy in statistical physics, achieving effective reconstruction of the optimal conditional distribution.The proposed algorithm requires training only a single neural network and circumvents the challenge of computing the normalization factor in energy-based models using the Markov chain Monte Carlo (MCMC) sampling. Experimental results demonstrate the significant effectiveness of the proposed algorithm in estimating high-dimensional RD functions and reconstructing the optimal conditional distribution.

cs.IT↗

arXiv2025

RDD Function: A Tradeoff Between Rate and Distortion-in-Distortion

In this paper, we propose a novel function named Rate Distortion-in-Distortion (RDD) function as an extension of the classical rate-distortion (RD) function, where the expected distortion constraint is replaced by a Gromov-type distortion. This distortion, integral to the Gromov-Wasserstein (GW) distance, effectively defines the similarity in spaces of possibly different dimensions even without a direct metric between them. While the RDD function qualifies as an informational RD function, encoding theorems substantiate its status as an operational RD function, thereby underscoring its potential applicability in real-world source coding. Due to the high computational complexity associated with Gromov-type distortion, in general, the RDD function cannot be evaluated analytically. Consequently, we develop an alternating mirror descent algorithm that significantly reduces computational complexity by employing decomposition, linearization, and relaxation techniques. Numerical results on classical sources and different grids demonstrate the effectiveness of the developed algorithm. By exploring the relationship between the RDD function and the RD function, we suggest that the RDD function may have potential applications in future scenarios.

cs.IT↗

arXiv2024

A Peaceman-Rachford Splitting Approach with Deep Equilibrium Network for Channel Estimation

Multiple-input multiple-output (MIMO) is pivotal for wireless systems, yet its high-dimensional, stochastic channel poses significant challenges for accurate estimation, highlighting the critical need for robust estimation techniques. In this paper, we introduce a novel channel estimation method for the MIMO system. The main idea is to construct a fixed-point equation for channel estimation, which can be implemented into the deep equilibrium (DEQ) model with a fixed network. Specifically, the Peaceman-Rachford (PR) splitting method is applied to the dual form of the regularized minimization problem to construct fixed-point equation with non-expansive property. Then, the fixed-point equation is implemented into the DEQ model with a fixed layer, leveraging its advantage of the low training complexity. Moreover, we provide a rigorous theoretical analysis, demonstrating the convergence and optimality of our approach. Additionally, simulations of hybrid far- and near-field channels demonstrate that our approach yields favorable results, indicating its ability to advance channel estimation in MIMO system.

eess.SP↗

arXiv2024

Alternating Maximization Algorithm for Mismatch Capacity with Oblivious Relaying

Reliable communication over a discrete memoryless channel with the help of a relay has aroused interest due to its widespread applications in practical scenarios. By considering the system with a mismatched decoder, previous works have provided optimization models to evaluate the mismatch capacity in these scenarios. The proposed models, however, are difficult due to the complicated structure of the mismatched decoding problem with the information flows in hops given by the relay. Existing methods, such as the grid search, become impractical as they involve finding all roots of a nonlinear system, with the growing size of the alphabet. To address this problem, we reformulate the max-min optimization model as a consistent maximization form, by considering the dual form of the inner minimization problem and the Lagrangian with a fixed multiplier. Based on the proposed formulation, an alternating maximization framework is designed, which provides the closed-form solution with simple iterations in each step by introducing a suitable variable transformation. The effectiveness of the proposed approach is demonstrated by the simulations over practical scenarios, including Quaternary and Gaussian channels. Moreover, the simulation results of the transitional probability also shed light on the promising application attribute to the quantizer design in the relay node.

cs.IT↗

arXiv2024

On Convergence of Discrete Schemes for Computing the Rate-Distortion Function of Continuous Source

Computing the rate-distortion function for continuous sources is commonly regarded as a standard continuous optimization problem. When numerically addressing this problem, a typical approach involves discretizing the source space and subsequently solving the associated discrete problem. However, existing literature has predominantly concentrated on the convergence analysis of solving discrete problems, usually neglecting the convergence relationship between the original continuous optimization and its associated discrete counterpart. This neglect is not rigorous, since the solution of a discrete problem does not necessarily imply convergence to the solution of the original continuous problem, especially for non-linear problems. To address this gap, our study employs rigorous mathematical analysis, which constructs a series of finite-dimensional spaces approximating the infinite-dimensional space of the probability measure, establishing that solutions from discrete schemes converge to those from the continuous problems.

cs.IT↗

arXiv2024

A Double Maximization Approach for Optimizing the LM Rate of Mismatched Decoding

An approach is established for maximizing the Lower bound on the Mismatch capacity (hereafter abbreviated as LM rate), a key performance bound in mismatched decoding, by optimizing the channel input probability distribution. Under a fixed channel input probability distribution, the computation of the corresponding LM rate is a convex optimization problem. When optimizing the channel input probability distribution, however, the corresponding optimization problem adopts a max-min formulation, which is generally non-convex and is intractable with standard approaches. To solve this problem, a novel dual form of the LM rate is proposed, thereby transforming the max-min formulation into an equivalent double maximization formulation. This new formulation leads to a maximization problem setup wherein each individual optimization direction is convex. Consequently, an alternating maximization algorithm is established to solve the resultant maximization problem setup. Each step of the algorithm only involves a closed-form iteration, which is efficiently implemented with standard optimization procedures. Numerical experiments show the proposed approach for optimizing the LM rate leads to noticeable rate gains.

cs.IT↗

arXiv2024

An Expectation-Maximization Relaxed Method for Privacy Funnel

The privacy funnel (PF) gives a framework of privacy-preserving data release, where the goal is to release useful data while also limiting the exposure of associated sensitive information. This framework has garnered significant interest due to its broad applications in characterization of the privacy-utility tradeoff. Hence, there is a strong motivation to develop numerical methods with high precision and theoretical convergence guarantees. In this paper, we propose a novel relaxation variant based on Jensen's inequality of the objective function for the computation of the PF problem. This model is proved to be equivalent to the original in terms of optimal solutions and optimal values. Based on our proposed model, we develop an accurate algorithm which only involves closed-form iterations. The convergence of our algorithm is theoretically guaranteed through descent estimation and Pinsker's inequality. Numerical results demonstrate the effectiveness of our proposed algorithm.

cs.IT↗

arXiv2024

Efficient and Provably Convergent Computation of Information Bottleneck: A Semi-Relaxed Approach

Information Bottleneck (IB) is a technique to extract information about one target random variable through another relevant random variable. This technique has garnered significant interest due to its broad applications in information theory and deep learning. Hence, there is a strong motivation to develop efficient numerical methods with high precision and theoretical convergence guarantees. In this paper, we propose a semi-relaxed IB model, where the Markov chain and transition probability condition are relaxed from the relevance-compression function. Based on the proposed model, we develop an algorithm, which recovers the relaxed constraints and involves only closed-form iterations. Specifically, the algorithm is obtained by analyzing the Lagrangian of the relaxed model with alternating minimization in each direction. The convergence property of the proposed algorithm is theoretically guaranteed through descent estimation and Pinsker's inequality. Numerical experiments across classical and discrete distributions corroborate the analysis. Moreover, our proposed algorithm demonstrates notable advantages in terms of computational efficiency, evidenced by significantly reduced run times compared to existing methods with comparable accuracy.

cs.IT↗

arXiv2024

A Constrained BA Algorithm for Rate-Distortion and Distortion-Rate Functions

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 with a fixed multiplier. In this paper, we propose a novel modification of the BA algorithm, wherein the multiplier is updated through a one-dimensional root-finding step using a monotonic univariate function, efficiently implemented by Newton's method in each iteration. Consequently, the modified algorithm directly computes the RD function for a given target distortion, without exploring the entire RD curve as in the original BA algorithm. Moreover, this modification presents a versatile framework, applicable to a wide range of problems, including the computation of distortion-rate (DR) functions. Theoretical analysis shows that the outputs of the modified algorithms still converge to the solutions of the RD and DR functions with rate $O(1/n)$, where $n$ is the number of iterations. Additionally, these algorithms provide $\varepsilon$-approximation solutions with $O\left(\frac{MN\log N}{\varepsilon}(1+\log |\log \varepsilon|)\right)$ arithmetic operations, where $M,N$ are the sizes of source and reproduced alphabets respectively. Numerical experiments demonstrate that the modified algorithms exhibit significant acceleration compared with the original BA algorithms and showcase commendable performance across classical source distributions such as discretized Gaussian, Laplacian and uniform sources.

cs.IT↗

arXiv2023

Information Bottleneck Revisited: Posterior Probability Perspective with Optimal Transport

Information bottleneck (IB) is a paradigm to extract information in one target random variable from another relevant random variable, which has aroused great interest due to its potential to explain deep neural networks in terms of information compression and prediction. Despite its great importance, finding the optimal bottleneck variable involves a difficult nonconvex optimization problem due to the nonconvexity of mutual information constraint. The Blahut-Arimoto algorithm and its variants provide an approach by considering its Lagrangian with fixed Lagrange multiplier. However, only the strictly concave IB curve can be fully obtained by the BA algorithm, which strongly limits its application in machine learning and related fields, as strict concavity cannot be guaranteed in those problems. To overcome the above difficulty, we derive an entropy regularized optimal transport (OT) model for IB problem from a posterior probability perspective. Correspondingly, we use the alternating optimization procedure and generalize the Sinkhorn algorithm to solve the above OT model. The effectiveness and efficiency of our approach are demonstrated via numerical experiments.

cs.IT↗

arXiv2023

Computation of Rate-Distortion-Perception Functions With Wasserstein Barycenter

The nascent field of Rate-Distortion-Perception (RDP) theory is seeing a surge of research interest due to the application of machine learning techniques in the area of lossy compression. The information RDP function characterizes the three-way trade-off between description rate, average distortion, and perceptual quality measured by discrepancy between probability distributions. However, computing RDP functions has been a challenge due to the introduction of the perceptual constraint, and existing research often resorts to data-driven methods. In this paper, we show that the information RDP function can be transformed into a Wasserstein Barycenter problem. The nonstrictly convexity brought by the perceptual constraint can be regularized by an entropy regularization term. We prove that the entropy regularized model converges to the original problem. Furthermore, we propose an alternating iteration method based on the Sinkhorn algorithm to numerically solve the regularized optimization problem. Experimental results demonstrate the efficiency and accuracy of the proposed algorithm.

cs.IT↗

arXiv2022

A Communication Optimal Transport Approach to the Computation of Rate Distortion Functions

In this paper, we propose a new framework named Communication Optimal Transport (CommOT) for computing the rate distortion (RD) function. This work is motivated by observing the fact that the transition law and the relative entropy in communication theory can be viewed as the transport plan and the regularized objective function in the optimal transport (OT) model. However, unlike in classical OT problems, the RD function only possesses one-side marginal distribution. Hence, to maintain the OT structure, we introduce slackness variables to fulfill the other-side marginal distribution and then propose a general framework (CommOT) for the RD function. The CommOT model is solved via the alternating optimization technique and the well-known Sinkhorn algorithm. In particular, the expected distortion threshold can be converted into finding the unique root of a one-dimensional monotonic function with only a few steps. Numerical experiments show that our proposed framework (CommOT) for solving the RD function with given distortion threshold is efficient and accurate.

cs.IT↗

arXiv2022

An Optimal Transport Approach to the Computation of the LM Rate

Mismatch capacity characterizes the highest information rate for a channel under a prescribed decoding metric, and is thus a highly relevant fundamental performance metric when dealing with many practically important communication scenarios. Compared with the frequently used generalized mutual information (GMI), the LM rate has been known as a tighter lower bound of the mismatch capacity. The computation of the LM rate, however, has been a difficult task, due to the fact that the LM rate involves a maximization over a function of the channel input, which becomes challenging as the input alphabet size grows, and direct numerical methods (e.g., interior point methods) suffer from intensive memory and computational resource requirements. Noting that the computation of the LM rate can also be formulated as an entropy-based optimization problem with constraints, in this work, we transform the task into an optimal transport (OT) problem with an extra constraint. This allows us to efficiently and accurately accomplish our task by using the well-known Sinkhorn algorithm. Indeed, only a few iterations are required for convergence, due to the fact that the formulated problem does not contain additional regularization terms. Moreover, we convert the extra constraint into a root-finding procedure for a one-dimensional monotonic function. Numerical experiments demonstrate the feasibility and efficiency of our OT approach to the computation of the LM rate.

cs.IT↗