Resistive random-access memory (ReRAM)-based architectures can be used to accelerate Convolutional Neural Network (CNN) training. However, existing architectures either do not support normalization at all or they support only a limited version of it. …
Mobile system-on-chips (SoCs) are growing in their complexity and heterogeneity (e.g., Arm Big-Little architecture) to meet the needs of emerging applications, including games and artificial intelligence. This makes it very challenging to optimally …
Bayesian optimization (BO) is an efficient framework for solving black-box optimization problems with expensive function evaluations. This paper addresses the BO problem setting for combinatorial spaces (e.g., sequences and graphs) that occurs …
We consider the problem of optimizing expensive black-box functions over discrete spaces (e.g., sets, sequences, graphs). The key challenge is to select a sequence of combinatorial structures to evaluate, in order to identify high-performing …
We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto set of solutions while minimizing the number of function evaluations. For example, in …
Efficiency of power management system (PMS) is one of the key performance metrics for highly integrated system on chips (SoCs). Towards the goal of improving power efficiency of SoCs, we make two key technical contributions in this paper. First, we …
We study the novel problem of blackbox optimization of multiple objectives via multi-fidelity function evaluations that vary in the amount of resources consumed and their accuracy. The overall goal is to approximate the true Pareto set of solutions …
We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto-set of solutions by minimizing the number of function evaluations. For example, in hardware …
In a structured prediction problem, one needs to learn a predictor that, given a structured input, produces a structured object, such as a sequence, tree, or clustering output. Prototypical structured prediction tasks include part-of-speech tagging …
In a structured prediction problem, we need to learn a predictor that can produce a structured output given a structured input (eg, part-of-speech tagging). The key learning and inference challenge is due to the exponential size of the structured …