• Corpus ID: 239768672

Learning in Multi-Stage Decentralized Matching Markets

@inproceedings{Dai2021LearningIM,
  title={Learning in Multi-Stage Decentralized Matching Markets},
  author={Xiaowu Dai and Michael I. Jordan},
  booktitle={Neural Information Processing Systems},
  year={2021}
}
Matching markets are often organized in a multi-stage and decentralized manner. Moreover, participants in real-world matching markets often have uncertain preferences. This article develops a framework for learning optimal strategies in such settings, based on a nonparametric statistical approach and variational analysis. We propose an efficient algorithm, built upon concepts of “lower uncertainty bound” and “calibrated decentralized matching,” for maximizing the participants’ expected payoff… 

Figures and Tables from this paper

Double Matching Under Complementary Preferences

A new algorithm for addressing the problem of matching markets with complementary preferences, where agents’ preferences are unknown a priori and must be learned from data, called the Multi-agent Multi-type Thompson Sampling (MMTS) algorithm.

Thompson Sampling for Bandit Learning in Matching Markets

The first regret analysis for TS in the new setting of iterative matching markets is provided, demonstrating the practical advantages of the TS-type algorithm over the ETC and UCB-type baselines.

Competing Bandits in Time Varying Matching Markets

The Restart Competing Bandits (RCB) algorithm is proposed, which combines a simple restart strategy to handle the non-stationarity with the competing bandits algorithm (Liu et al., 2020) designed for the stationary case.

Rate-Optimal Contextual Online Matching Bandit

A Centralized Contextual Explore Then Commit (CC-ETC) algorithm to adapt to the COMBO, which solves online matching with dynamic preference and achieves a sublinear regret upper bound O(log(T )) and is a rate-optimal algorithm by proving a matching lower bound.

Statistical Inference for Fisher Market Equilibrium

Statistical inference under market equilibrium effects has attracted increasing attention recently. In this paper we focus on the specific case of linear Fisher markets. They have been widely use in

RATE-OPTIMAL CONTEXTUAL ONLINE MATCHING BANDIT

CC-ETC solves online matching with dynamic preference and is a rate-optimal algorithm by proving a matching lower bound, and is robust to variant preference schemes, dimensions of contexts, reward noise levels, and context variation levels.

Double Auctions with Two-sided Bandit Feedback

Double Auction enables decentralized transfer of goods between multiple buyers and sellers, thus underpinning functioning of many online marketplaces. Buyers and sellers compete in these markets

Incentive-Aware Recommender Systems in Two-Sided Markets

Online platforms in the Internet Economy commonly incorporate recommender systems that recommend arms (e.g., products) to agents (e.g., users). In such platforms, a myopic agent has a natural

Robust multi-item auction design using statistical learning: Overcoming uncertainty in bidders' types distributions

The proposed approach utilizes nonparametric density estimation to accurately estimate bidders’ types from historical bids’ data, and is built upon the Vickrey-Clarke-Groves mechanism, ensuring satisfaction of Bayesian incentive compatibility (BIC) and δ -individual rationality (IR).

References

SHOWING 1-10 OF 40 REFERENCES

Learning Strategies in Decentralized Matching Markets under Uncertain Preferences

An optimal strategy is derived that maximizes the agent's expected payoff and calibrate the uncertain state by taking the opportunity costs into account and proves a fairness property that asserts that there exists no justified envy according to the proposed strategy.

Competing Bandits in Matching Markets

This work proposes a statistical learning model in which one side of the market does not have a priori knowledge about its preferences for the other side and is required to learn these from stochastic rewards.

Bandit Learning in Decentralized Matching Markets

This model extends the standard stochastic multi-armed bandit framework to a decentralized multiple player setting with competition and introduces a new algorithm for this setting that attains stable regret when preferences of the arms over players are shared.

Two-Sided Bandits and the Dating Market

We study the decision problems facing agents in repeated matching environments with learning, or two-sided bandit problems, and examine the dating market, in which men and women repeatedly go out on

A Supply and Demand Framework for Two-Sided Matching Markets

This paper develops a price-theoretic framework for matching markets with heterogeneous preferences. The model departs from the Gale and Shapley model by assuming that a finite number of agents on

Ex Ante Price Offers in Matching Games Non-steady States

A matching problem is considered in which sellers can publicly commit to a trading price that differs from the price at which buyers expect to trade elsewhere in the market. When demand and supply

A search model of two-sided matching under nontransferable utility

Information Acquisition in Matching Markets: The Role of Price Discovery

It is shown regret-free stable outcomes exist, and finding them is equivalent to finding appropriately-defined market-clearing cutoffs, and it is suggested approaches for facilitating efficient price discovery, leveraging historical information or market sub-samples to estimate cutoffs.

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

The focus is on two extreme cases in which the analysis of regret is particularly simple and elegant: independent and identically distributed payoffs and adversarial payoffs.