9 papers
Chi-Squared Geometry for Robust Finite-Blocklength Information and Dispersion Analysis
Hassan Tavakoli, Thinh Nguyen, Bella Bose
We develop a column-wise chi-squared geometry for discrete memoryless channels (DMCs) yielding tight, logarithm-free bounds on mutual information, channel dispersion, and finite-bl…
Combinatorial Capacity Bounds for the -ary Deletion Channel
Hassan Tavakoli, Thinh Nguyen, Bella Bose
We study the \(q\)-ary deletion channel via the pattern-count scalar \(N_n(x,y)\), the number of deletion subsets mapping \(x\inΣ_q^n\) to \(y\inΣ_q^k\), which factorizes the trans…
BSO: Safety Alignment Is Density Ratio Matching
Tien-Phat Nguyen, Truong Nguyen, Thin Nguyen +3
Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement learning, and primal-dual update…
RankGuardPolar Private Public Finite Length Polar Codes with Rank-Certified Leakage
Hassan Tavakoli, Thinh Nguyen, Bella Bose
We introduce \textbf{RankGuard-Polar}, a framework for safely publishing a subset of polar codeword coordinates over shared public resources. We assume a strong eavesdropper who ha…
Parameter Estimation of Mutual Information Maximized Channels
Hassan Tavakoli, Thinh Nguyen, Bella Bose
We study the problem of estimating a parametric discrete memoryless channel \( p(y \mid x; \boldsymbolθ) \) when the transmitter selects its input distribution \( π\) to maximize m…
Cross-Domain Lossy Compression via Constrained Minimum Entropy Coupling
Nam Nguyen, Hassan Tavakoli, An Vuong +2
This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes…
Perception-based Image Denoising via Generative Compression
Nam Nguyen, Thinh Nguyen, Bella Bose
Image denoising aims to remove noise while preserving structural details and perceptual realism, yet distortion-driven methods often produce over-smoothed reconstructions, especial…
Rate-Distortion-Classification Representation Theory for Bernoulli Sources
Nam Nguyen, Thinh Nguyen, Bella Bose
We study task-oriented lossy compression through the lens of rate-distortion-classification (RDC) representations. The source is Bernoulli, the distortion measure is Hamming, and t…
Universal Rate-Distortion-Classification Representations for Lossy Compression
Nam Nguyen, Thuan Nguyen, Thinh Nguyen +1
In lossy compression, Wang et al. [1] recently introduced the rate-distortion-perception-classification function, which supports multi-task learning by jointly optimizing perceptua…