More Like this

1. Cellular Network Configuration via Online Learning and Joint Optimization

   Guo, Xueying; Trimponiasy, George; Wang, Xiaoxiao; Chen, Zhitang; Geng, Yanhui; Liu, Xin (January 2017, IEEE Big Data Conference)

   Cellular network configuration is critical for network performance. Current practice is labor-intensive, errorprone, and far from optimal. To automate efficient cellular network configuration, in this work, we propose an onlinelearning-based joint-optimization approach that addresses a few specific challenges: limited data availability, convoluted sample data, highly complex optimization due to interactions among neighboring cells, and the need to adapt to network dynamics. In our approach, to learn an appropriate utility function for a cell, we develop a neural-network-based model that addresses the convoluted sample data issue and achieves good accuracy based on data aggregation. Based on the utility function learned, we formulate a global network configuration optimization problem. To solve this high-dimensional nonconcave maximization problem, we design a Gibbs-samplingbased algorithm that converges to an optimal solution when a technical parameter is small enough. Furthermore, we design an online scheme that updates the learned utility function and solves the corresponding maximization problem efficiently to adapt to network dynamics. To illustrate the idea, we use the case study of pilot power configuration. Numerical results illustrate the effectiveness of the proposed approach. 

   more » « less
2. Optimization Under Uncertainty Versus Algebraic Heuristics: A Research Method for Comparing Computational Design Methods

   Binder, William R.; Paredis, Christiaan J.J. (August 2017, Proceedings of the ASME 2017 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference)

   In this paper, we introduce a research method for comparing computational design methods. This research method addresses the challenge of measuring the difference in performance of different design methods in a way that is fair and unbiased with respect to differences in modeling abstraction, accuracy and uncertainty representation. The method can be used to identify the conditions under which each design method is most beneficial. To illustrate the research method, we compare two design methods for the design of a pressure vessel: 1) an algebraic approach, based on the ASME pressure vessel code, which accounts for uncertainty implicitly through safety factors, and 2) an optimization-based, expected-utility maximization approach which accounts for uncertainty explicitly. The computational experiments initially show that under some conditions the algebraic heuristic surprisingly outperforms the optimization-based approach. Further analysis reveals that an optimization-based approach does perform best as long as the designer applies good judgment during uncertainty elicitation. An ignorant or overly confident designer is better off using safety factors. 

   more » « less
3. Multi‐objective Bayesian algorithm automatically discovers low‐cost high‐growth serum‐free media for cellular agriculture application

   https://doi.org/10.1002/elsc.202300005  

   Cosenza, Zachary; Block, David E.; Baar, Keith; Chen, Xingyu (August 2023, Engineering in Life Sciences)

   Abstract In this work, we applied a multi‐information source modeling technique to solve a multi‐objective Bayesian optimization problem involving the simultaneous minimization of cost and maximization of growth for serum‐free C2C12 cells using a hyper‐volume improvement acquisition function. In sequential batches of custom media experiments designed using our Bayesian criteria, collected using multiple assays targeting different cellular growth dynamics, the algorithm learned to identify the trade‐off relationship between long‐term growth and cost. We were able to identify several media with more growth of C2C12 cells than the control, as well as a medium with 23% more growth at only 62.5% of the cost of the control. These algorithmically generated media also maintained growth far past the study period, indicating the modeling approach approximates the cell growth well from an extremely limited data set. 

   more » « less
4. Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

   Li, Yeshu; Shi, Zhan; Zhang, Xinhua; Ziebart, Brian (March 2022, International Conference on Artificial Intelligence and Statistics)

   We consider the problem of learning the underlying structure of a general discrete pairwise Markov network. Existing approaches that rely on empirical risk minimization may perform poorly in settings with noisy or scarce data. To overcome these limitations, we propose a computationally efficient and robust learning method for this problem with near-optimal sample complexities. Our approach builds upon distributionally robust optimization (DRO) and maximum conditional log-likelihood. The proposed DRO estimator minimizes the worst-case risk over an ambiguity set of adversarial distributions within bounded transport cost or f-divergence of the empirical data distribution. We show that the primal minimax learning problem can be efficiently solved by leveraging sufficient statistics and greedy maximization in the ostensibly intractable dual formulation. Based on DRO’s approximation to Lipschitz and variance regularization, we derive near-optimal sample complexities matching existing results. Extensive empirical evidence with different corruption models corroborates the effectiveness of the proposed methods. 

   more » « less
5. Learning to Solve Linear Inverse Problems in Imaging with Neumann Networks

   Ongie, Greg; Gilton, Davis; Willett, Rebecca (December 2019, NeurIPS 2019 Workshop on Solving Inverse Problems with Deep Networks)

   Recent advances have illustrated that it is often possible to learn to solve linear inverse problems in imaging using training data that can outperform more traditional regularized least-squares solutions. Along these lines, we present some extensions of the Neumann network, a recently introduced end-to-end learned architecture inspired by a truncated Neumann series expansion of the solution map to a regularized least-squares problem. Here we summarize the Neumann network approach and show that it has a form compatible with the optimal reconstruction function for a given inverse problem. We also investigate an extension of the Neumann network that incorporates a more sample efficient patch-based regularization approach. 

   more » « less