Preferred Design of Hierarchical Distribution Matching
Distribution matching and dematching (DM/invDM) are key functions in probabilistic shaping (PS). Recently techniques for low complexity implementation of DM/invDM have been well studied. Our previously proposed hierarchical DM (HiDM) is one of the good candidates, with capacity-approaching performance with reasonable hardware resources. Though we explained the recipe of HiDM construction with a small example having a short DM word length, there might still be difficulties to expand it to longer DM word lengths. To improve the reproducibility of our work, this paper explains the key parameters in an HiDM having a DM word length more than 100 symbols.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Design Strategy Network: A deep hierarchical framework to represent generative design strategies in complex action spaces
Generative design problems often encompass complex action spaces that may be divergent over time, contain state-dependent constraints, or involve hybrid (discrete and continuous) domains. To address those challenges, thi…
Hierarchical Rectified Flow Matching with Mini-Batch Couplings
Flow matching has emerged as a compelling generative modeling approach that is widely used across domains. To generate data via a flow matching model, an ordinary differential equation (ODE) is numerically solved via for…
Representation Distribution Matching for One-Step Visual Generation
We elucidate the design space of Representation Distribution Matching (RDM), our name for the paradigm that trains a one-step image generator by matching generated and reference feature distributions under frozen pretrai…
Hierarchical Discrete Distribution Decomposition for Match Density Estimation
Explicit representations of the global match distributions of pixel-wise correspondences between pairs of images are desirable for uncertainty estimation and downstream applications. However, the computation of the match…
Density EstimationOptical Flow EstimationStereo MatchingStereo Matching HandDistribution Matching via Generalized Consistency Models
Recent advancement in generative models have demonstrated remarkable performance across various data modalities. Beyond their typical use in data synthesis, these models play a crucial role in distribution matching tasks…
Domain Adaptation