Quadratic Signaling With Prior Mismatch at an Encoder and Decoder: Equilibria, Continuity, and Robustness Properties
نویسندگان
چکیده
We consider communications through a Gaussian noise channel between an encoder and decoder which have subjective probabilistic models on the source distribution. Although they same cost function, induced expected costs are misaligned due to their prior mismatch, requires game-theoretic approach. two approaches: Nash setup, with no commitment, Stackelberg solution concept, where is committed given announced policy a priori . show that equilibrium of upper semicontinuous, under Wasserstein metric, as encoder’s approaches decoder’s prior, it also lower semicontinuous priors. For optimality affine policies for signaling longer holds thus, team-theoretic linear/affine not robust perturbations. provide conditions there exist informative equilibria policies. Finally, we existence fully cheap talk problem absolute continuity condition.
منابع مشابه
Skip-graph: Learning Graph Embeddings with an Encoder-decoder Model
In this work, we study the problem of feature representation learning for graphstructured data. Many of the existing work in the area are task-specific and based on supervised techniques. We study a method for obtaining a generic feature representation for a graph using an unsupervised approach. The neural encoderdecoder model is a method that has been used in the natural language processing do...
متن کاملData-hiding with host state at the encoder and partial side information at the decoder
In this paper, we extend a traditional robust datahiding set-up with host state at the encoder to a case when a partial side information about host statistics is also available at the decoder. We demonstrate that the knowledge of host statistics at the decoder can relax the critical requirements of random binning-based methods concerning attack channel statistics at the encoder. We also analyze...
متن کاملOn the Properties of Neural Machine Translation: Encoder-Decoder Approaches
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on a...
متن کاملJapanese Text Normalization with Encoder-Decoder Model
Text normalization is the task of transforming lexical variants to their canonical forms. We model the problem of text normalization as a character-level sequence to sequence learning problem and present a neural encoder-decoder model for solving it. To train the encoder-decoder model, many sentences pairs are generally required. However, Japanese non-standard canonical pairs are scarce in the ...
متن کاملFamilies of linear-quadratic problems : continuity properties
In this paper we investigate for g1ven one-parameter families of linear time-invariant finite-dimensional systems the parameter dependence of the linear-quadratic optimal cost, optimal control inputs, optimal state-trajectories and optimal outputs. It 1S shown that results that have been obtained in the past in the context of the problem of 'cheap control' can in fact be generalized to a much b...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Automatic Control
سال: 2023
ISSN: ['0018-9286', '1558-2523', '2334-3303']
DOI: https://doi.org/10.1109/tac.2022.3142121