DeepAI AI Chat
Log In Sign Up

On the Impossibility of Convex Inference in Human Computation

by   Nihar B. Shah, et al.
berkeley college

Human computation or crowdsourcing involves joint inference of the ground-truth-answers and the worker-abilities by optimizing an objective function, for instance, by maximizing the data likelihood based on an assumed underlying model. A variety of methods have been proposed in the literature to address this inference problem. As far as we know, none of the objective functions in existing methods is convex. In machine learning and applied statistics, a convex function such as the objective function of support vector machines (SVMs) is generally preferred, since it can leverage the high-performance algorithms and rigorous guarantees established in the extensive literature on convex optimization. One may thus wonder if there exists a meaningful convex objective function for the inference problem in human computation. In this paper, we investigate this convexity issue for human computation. We take an axiomatic approach by formulating a set of axioms that impose two mild and natural assumptions on the objective function for the inference. Under these axioms, we show that it is unfortunately impossible to ensure convexity of the inference problem. On the other hand, we show that interestingly, in the absence of a requirement to model "spammers", one can construct reasonable objective functions for crowdsourcing that guarantee convex inference.


page 1

page 2

page 3

page 4


Convexification of Learning from Constraints

Regularized empirical risk minimization with constrained labels (in cont...

When can l_p-norm objective functions be minimized via graph cuts?

Techniques based on minimal graph cuts have become a standard tool for s...

Correcting Convexity Bias in Function and Functional Estimate

A general framework with a series of different methods is proposed to im...

Statistical mechanics of the inverse Ising problem and the optimal objective function

The inverse Ising problem seeks to reconstruct the parameters of an Isin...

Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent

Although the optimization objectives for learning neural networks are hi...

Computational Design with Crowds

Computational design is aimed at supporting or automating design process...

Hyperloop System Optimization

Hyperloop system design is a uniquely coupled problem because it involve...