Sam Nazari

Risto Miikkulainen, Neil Iscoe, Aaron Shagrin et al.

Conversion optimization means designing a web interface so that as many users as possible take a desired action on it, such as register or purchase. Such design is usually done by hand, testing one change at a time through A/B testing, or a limited number of combinations through multivariate testing, making it possible to evaluate only a small fraction of designs in a vast design space. This paper describes Sentient Ascend, an automatic conversion optimization system that uses evolutionary optimization to create effective web interface designs. Ascend makes it possible to discover and utilize interactions between the design elements that are difficult to identify otherwise. Moreover, evaluation of design candidates is done in parallel online, i.e. with a large number of real users interacting with the system. A case study on an existing media site shows that significant improvements (i.e. over 43%) are possible beyond human design. Ascend can therefore be seen as an approach to massively multivariate conversion optimization, based on a massively parallel interactive evolution.

Sam Nazari, Bahram Shafai, Amirreza Oghbaee

Positive systems are important class of dynamic systems with impressive properties. The response of such systems to positive initial conditions and positive inputs remain in the nonnegative orthant of the state space. Although positive observers have been designed for positive systems, they are unable to estimate the states when unknown inputs or disturbances are present in the systems. This paper is a first attempt to design positive unknown input observers (PUIO) for positive linear systems. The structural constraints on observer parameters make the design task cumbersome. However, with the aid of a positive stabilization scheme via LMI and by imposing conditions on positivity of the generalized inverse associated with a certain design matrix, we provide a reliable procedure for the design of PUIOs.

Sam Nazari

This brief memo reviews the theory of Unknown Input Observers (UIO) for state estimation in systems subject to disturbance inputs that are not known a priori. One main advantage of the UIO is that the observer structure naturally decouples the plant inputs from the state estimation process. This advantage is highlighted in three example dynamic systems commonly found in control theory. It is shown that the estimation error for all three systems asymptotically approaches zero by application of the UIO under the influence of dynamic disturbances.