鄭宇庭

Bio: 鄭宇庭 is an academic researcher. The author has an hindex of 1, co-authored 1 publications receiving 3235 citations.

The Social Responsibility of Business Is to Increase Its Profits

Abstract: When I hear businessmen speak eloquently about the “social responsibilities of business in a free-enterprise system”, I am reminded of the wonderful line about the Frenchman who discovered at the age of 70 that he had been speaking prose all his life. The businessmen believe that they are defending free enterprise when they declaim that business is not concerned “merely” with profit but also with promoting desirable “social” ends; that business has a “social conscience” and takes seriously its responsibilities for providing employment, eliminating discrimination, avoiding pollution and whatever else may be the catchwords of the contemporary crop of reformers. In fact they are — or would be if they or anyone else took them seriously -preaching pure and unadulterated socialism. Businessmen who talk this way are unwitting puppets of the intellectual forces that have been undermining the basis of a free society these past decades.

Convex multi-task feature learning

Abstract: We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known single-task 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across-tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select--not learn--a few common variables across the tasks.