arXiv subjects

Mohammad Reza Deylam Salehi

Publications and source records attributed to Mohammad Reza Deylam Salehi.

9 recordsLinked to original sources

arXiv2026

Support-Aware Telemetry Compression for 5G Positioning via Conditional Conflict Graphs

Geographically separated transmission/reception points (TRPs) report quantized measurements to a Location Management Function (LMF), even when the application requires only a coarse location region. We formulate this task as a distributed zero-error function-computation problem, in which each TRP transmits an index sufficient for the LMF to reproduce the required service decision. Since positioning geometry induces a sparse and nonrectangular support, independently constructed per-terminal characteristic-graph colorings are not necessarily jointly decodable. We introduce a conditional conflict graph that exactly characterizes valid single-terminal updates and develop an alternating codebook construction that preserves global zero-error decodability. In a reproducible three-TRP study with range-equivalent timing measurements and $120$ native bins, all resulting codebooks satisfy an explicit decoder-conflict test. For service-cell sizes up to $100$ m, the achieved ideal rate is $5.38$--$5.44$ bits per epoch per TRP, compared with $6.91$ bits for raw reporting and $6.56$--$6.87$ bits for a globally valid interval-based baseline. A complementary measured six-base-station TDoA study shows that $83.77\%$ of the learned native support recurs on an independent trajectory. For these recurrent tuples, the codebooks preserve the service decision exactly and reduce the ideal rate by $22.8$--$35.6\%$ for $2$--$8$ m service grids. The feasible report-tuple set also provides a single-epoch geometric-consistency check under injected timing bias. Finally, we identify the NRPPa/OpenAirInterface integration points and safeguards required for experimental implementation.

cs.NI↗

arXiv2026

Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating

In-network learning (INL) trains distributed neural modules by exchanging latent activations and backpropagated errors over a communication graph. This letter proposes Dijkstra-pruned INL (D-INL), which removes non-tree links by retaining a capacity-aware shortest-path tree rooted at the fusion node. To balance sparsity and predictive information, local routing (or aggregation) is modeled as a finite-rate stochastic gate with rate $R_g=I(Z; T)$. We derive a rate-distortion-generalization bound and validate the method on a reproducible distributed-classification experiment, where D-INL reduces training exchange by $70.4\%$ while preserving accuracy within the standard deviation of dense INL. Adding finite-rate regularization further reduces the estimated latent rate by $45.7\%$ relative to unregularized Dijkstra INL.

cs.IT↗

arXiv2026

Expert Routing for Communication-Efficient MoE via Finite Expert Banks

Resource-efficient machine learning increasingly uses sparse Mixture-of-Experts (MoE) architectures, where the gate acts as both a learning component and a routing interface controlling computation, communication, and accuracy. Motivated by finite-rate interpretations of MoE gating, we treat the gate as a stochastic channel and use $I(X;T)$ to quantify the routing information available to the selected expert. To make the associated information quantities tractable beyond synthetic examples, we develop a finite-bank MNIST construction using pretrained CNN experts and a discrete, data-dependent selection rule. Since the selected model belongs to a finite candidate set, the algorithmic mutual information $I(S;W)$ admits a closed-form discrete-entropy estimator from the empirical posterior $q(W|S)$. Sweeping a data-dependence parameter $α$, we observe that $\widehat I(S;W)$ monotonically tracks the generalization gap, while the Xu-Raginsky bound exhibits the expected looseness. We also compare with a uniform union-bound baseline and introduce an empirical estimator of $I(X;T)$ together with a Blahut-Arimoto procedure for tracing an accuracy-rate curve over the expert bank. The proposed framework provides a practical tool for analyzing resource-aware MoE inference systems and for interpreting $I(X;T)$ and $D(R_g)$ as design proxies for efficient expert routing.

cs.LG↗

arXiv2026

Mixture-of-Experts under Finite-Rate Gating: Communication--Generalization Trade-offs

Mixture-of-Experts (MoE) architectures decompose prediction tasks into specialized expert sub-networks selected by a gating mechanism. This letter adopts a communication-theoretic view of MoE gating, modeling the gate as a stochastic channel operating under a finite information rate. Within an information-theoretic learning framework, {we specialize a mutual-information generalization bound and develop a rate-distortion characterization $D(R_g)$ of finite-rate gating, where $R_g:=I(X; T)$, yielding (under a standard empirical rate-distortion optimality condition) $\mathbb{E}[R(W)] \le D(R_g)+δ_m+\sqrt{(2/m)\, I(S; W)}$. }The analysis yields capacity-aware limits for communication-constrained MoE systems, and numerical simulations on synthetic multi-expert models empirically confirm the predicted trade-offs between gating rate, expressivity, and generalization.

stat.ML↗

arXiv2026

Learning-Augmented Perfectly Secure Collaborative Matrix Multiplication

This paper presents a perfectly secure matrix multiplication (PSMM) protocol for multiparty computation (MPC) of $\mathrm{A}^{\top}\mathrm{B}$ over finite fields. The proposed scheme guarantees correctness and information-theoretic privacy against threshold-bounded, semi-honest colluding agents, under explicit local storage constraints. Our scheme encodes submatrices as evaluations of sparse masking polynomials and combines coefficient alignment with Beaver-style randomness to ensure perfect secrecy. We demonstrate that any colluding set of parties below the security threshold observes uniformly random shares, and that the recovery threshold is optimal, matching existing information-theoretic limits. Building on this framework, we introduce a learning-augmented extension that integrates tensor-decomposition-based local block multiplication, capturing both classical and learned low-rank methods. We demonstrate that the proposed learning-based PSMM preserves privacy and recovery guarantees for MPC, while providing scalable computational efficiency gains (up to $80\%$) as the matrix dimensions grow.

cs.IT↗

arXiv2025

Typical Solutions of Multi-User Linearly-Decomposable Distributed Computing

We solve, in the typical-case sense, the multi-sender linearly-decomposable distributed computing problem introduced by tessellated distributed computing. We model real-valued encoders/decoders and demand matrices, and assess structural fidelity via a thresholded graph edit distance between the demand support and the two-hop support of the computed product. Our analysis yields: a closed-form second-moment (Frobenius) risk under spike-and-slab ensembles; deterministic links between thresholded GED and norm error; a Gaussian surrogate with sub-exponential tails that exposes explicit recall lines; concentration of GED and operator-norm control; and a compute-capped design with a visible knee. We map the rules to aeronautical and satellite networks.

cs.IT↗

arXiv2025

Distributed Compression for Computation and Bounds on the Optimal Rate

We address the problem of distributed computation of arbitrary functions of two correlated sources $X_1$ and $X_2$, residing in two distributed source nodes, respectively. We exploit the structure of a computation task by coding source characteristic graphs (and multiple instances using the $n$-fold OR product of this graph with itself). For regular graphs and general graphs, we establish bounds on the optimal rate -- characterized by the chromatic entropy for the $n$-fold graph products -- that allows a receiver for asymptotically lossless computation of arbitrary functions over finite fields. For the special class of cycle graphs (i.e., $2$-regular graphs), we establish an exact characterization of chromatic numbers and derive bounds on the required rates. Next, focusing on the more general class of $d$-regular graphs, we establish connections between $d$-regular graphs and expansion rates for $n$-fold graph powers using graph spectra. Finally, for general graphs, we leverage the Gershgorin Circle Theorem (GCT) to provide a characterization of the spectra, which allows us to build new bounds on the optimal rate. Our codes leverage the spectra of the computation and provide a graph expansion-based characterization to efficiently/succinctly capture the computation structure, providing new insights into the problem of distributed computation of arbitrary functions.

cs.IT↗

arXiv2025

Non-Linear Function Computation Broadcast

This work addresses the $K$-user computation broadcast problem consisting of a master node, that holds all datasets and users for a general class of function demands, including linear and non-linear functions, over finite fields. The master node sends a broadcast message to enable each of $K$ distributed users to compute its demanded function in an asymptotically lossless manner with user's side information. We derive bounds on the optimal $K$-user computation broadcast rate that allows the users to compute their demanded functions by capturing the structures of the computations and available side information. Our achievability scheme involves the design of a novel graph-based coding model to build a broadcast message to meet each user's demand, by leveraging the structural dependencies among the datasets, the user demands, and the side information of each user, drawing on K{ö}rner's characteristic graph framework. The converse uses the structures of the demands and the side information available at $K$ users to yield a tight lower bound on the broadcast rate. With the help of examples, we demonstrate our scheme achieves a better communication rate than the existing state of the art.

cs.IT↗

arXiv2024

Multi-Server Multi-Function Distributed Computation

The work here studies the communication cost for a multi-server multi-task distributed computation framework, and does so for a broad class of functions and data statistics. Considering the framework where a user seeks the computation of multiple complex (conceivably non-linear) tasks from a set of distributed servers, we establish communication cost upper bounds for a variety of data statistics, function classes and data placements across the servers. To do so, we proceed to apply, for the first time here, Körner's characteristic graph approach -- which is known to capture the structural properties of data and functions -- to the promising framework of multi-server multi-task distributed computing. Going beyond the general expressions, and in order to offer clearer insight, we also consider the well-known scenario of cyclic dataset placement and linearly separable functions over the binary field, in which case our approach exhibits considerable gains over the state of art. Similar gains are identified for the case of multi-linear functions.

cs.IT↗