|Author||Year||Abstract||Title (Click on the title to view the publication)|
|Steffen Keck, Wenjie Tang
We explore the joint effects of group decision making and group gender composition on the calibration of confidence judgments. Participants in two laboratory experiments, individually and in groups of three, stated confidence interval estimates for general-knowledge questions and for financial forecasts. Across both studies, our results reveal that groups with at least one female member are significantly better calibrated than all-male groups.
This effect is mediated by the extent to which group members share opinions and information during the group discussion. Moreover, we find that compared to a statistical aggregation of individual confidence intervals, group discussions have a neutral or positive effect on the quality of confidence judgments for groups with at least one female group member; in contrast, group discussion actually harms confidence calibration for all-male groups. Overall, our findings indicate that compared to all-male groups, even the inclusion of a small proportion of female members can have a strong effect on the quality of group confidence judgment.
|Gender Composition and Group Confidence Judgment: The Perils of All-Male Groups
|Wenjie Tang, Karan Girotra||2017||
We study the use of advance purchase discount (APD) contracts to incentivize a retailer to share demand information with a dual‐sourcing wholesaler. We analyze such contracts in terms of two practical considerations that are relevant in this context but have been overlooked by previous work that has largely studied the direct offer of APD to customers: the retailer's information acquisition cost and the wholesaler's limited information about that cost.
The wholesaler's limited knowledge of the retailer's cost leads to a departure—from the normal “full observability” APD design—that is asymmetric and depends on the extent of unobservability; if the uncertainty is small (resp., large) then the optimal discount is higher (resp., lower) than in the case of full observability. An APD contract that ignores the retailer's cost or the wholesaler's uncertainty about it will yield fewer benefits for the wholesaler and the supply chain. We offer a numerical illustration (calibrated on real industry data) establishing that for a representative product, an APD contract can improve the wholesaler's profit margin by as much as 3.5%.
|Using Advance Purchase Discount Contracts under Uncertain Information Acquisition Cost|
XUDONG LI, DEFENG SUN, AND KIM-CHUAN TOH
In applying the level-set method developed in [E. Van den Berg and M. P. Friedlander, SIAM J. Sci. Comput., 31 (2008), pp. 890–912] and [E. Van den Berg and M. P. Friedlander, SIAM J. Optim., 21 (2011), pp. 1201–1229] to solve the fused lasso problems, one needs to solve a sequence of regularized least squares subproblems. In order to make the level-set method practical, we develop a highly eﬃcient inexact semismooth Newton based augmented Lagrangian method for solving these subproblems.
The eﬃciency of our approach is based on several ingredients that constitute the main contributions of this paper. First, an explicit formula for constructing the generalized Jacobian of the proximal mapping of the fused lasso regularizer is derived. Second, the special structure of the generalized Jacobian is carefully extracted and analyzed for the eﬃcient implementation of the semismooth Newton method. Finally, numerical results, including the comparison between our approach and several state-of-the-art solvers, on real data sets are presented to demonstrate the high eﬃciency and robustness of our proposed algorithm in solving challenging large-scale fused lasso problems.
|On Efficiently Solving The Subproblems Of A Level-set Method For Fused Lasso Problems|
|Zhenzhen Yan, Sarah Yini Gao, Chung Piaw Teo||2018||
It is widely believed that a little ﬂexibility added at the right place can reap signiﬁcant beneﬁts for operations. Unfortunately, despite the extensive literature on this topic, we are not aware of any general methodology that can be used to guide managers in designing sparse (i.e., slightly ﬂexible) and yet eﬃcient operations. We address this issue using a distributionally robust approach to model the performance of a stochastic systemunderdiﬀerentprocessstructures.Weusethedualpricesobtainedfromarelated conic program to guide managers in the design process. This leads to a general solution methodologyfortheconstructionofeﬃcientsparsestructuresforseveralclassesofoperational problems.
Our approach can be used to design simple yet eﬃcient structures for workforcedeploymentandforanylevelofsparsityrequirement,torespondtodeviations and disruptions in the operational environment. Furthermore, in the case of the classical process ﬂexibility problem, our methodology can recover the k-chain structures that are knowntobeextremelyeﬃcientforthistypeofproblemwhenthesystemisbalancedand symmetric.Wecanalsoobtaintheanalogof2-chainfornonsymmetricalsystemusingthis methodology.
|On The Design Of Sparse but Eﬃcient Structures In Operations|
|Qi Fu, Chee-Khian Sim, Chung-Piaw Teo||2018||
How should decentralized supply chains set the profit sharing terms using
More specifically, we derive the relationshipsamong the optimal wholesale price set by the supplier, the order decision of theretailer, and the corresponding profit shares of each supply chain partner, based on the information available. Interestingly, in the distributionally robust setting, the correlation between demand and selling price has no bearing on the order decision of the retailer.
This allows us to simplify the solution structure of the profit sharing agreement problem
|Profit Sharing Agreements in Decentralized Supply Chains: A Distributionally Robust Approach|
|XUDONG LI, DEFENG SUN, AND KIM-CHUAN TOH
We develop a fast and robust algorithm for solving large-scale convex composite optimization models with an emphasis on the 1-regularized least squares regression (lasso) problems. Despite the fact that there exist a large number of solvers in the literature for the lasso problems, we found that no solver can eﬃciently handle diﬃcult large-scale regression problems with real data.
By leveraging on available error bound results to realize the asymptotic superlinear convergence property of the augmented Lagrangian algorithm, and by exploiting the second order sparsity of the problem through the semismooth Newton method, we are able to propose an algorithm, called Ssnal, to eﬃciently solve the aforementioned diﬃcult problems. Under very mild conditions, which hold automatically for lasso problems, both the primal and the dual iteration sequences generated by Ssnal possess a fast linear convergence rate, which can even be superlinear asymptotically. Numerical comparisons between our approach and a number of state-of-the-art solvers, on real data sets, are presented to demonstrate the high eﬃciency and robustness of our proposed algorithm in solving diﬃcult large-scale lasso problems.
|A Highly Efficient Semismooth Newton Augmented Lagrangian Method For Solving Lasso Problems|