이수민 교수

Random projection algorithm is of interest for constrained optimization when the constraint set is not known in advance or the projection operation on the whole constraint set is computationally prohibitive. This paper presents a distributed random projection algorithm for constrained convex optimization problems that can be used by multiple agents connected over a time-varying network, where each agent has its own objective function and its own constrained set. We prove that the iterates of all

We consider a decentralized online convex optimization problem in a network of agents, where each agent controls only a coordinate (or a part) of the global decision vector. For such a problem, we propose two decentralized stochastic variants (SODA-C and SODA-PS) of Nesterov's dual averaging method (DA), where each agent only uses a coordinate of the noise-corrupted gradient in the dual-averaging step. We show that the expected regret bounds for both algorithms have sublinear growth of O(√T), wi

We consider a distributed constrained convex optimization problem over a multi-agent (no central coordinator) network. We propose a completely decentralized and asynchronous gossip-based random projection (GRP) algorithm that solves the distributed problem using only local communications and computations. We analyze the convergence properties of the algorithm for a diminishing and a constant stepsize which are uncoordinated among agents. For a diminishing stepsize, we prove that the iterates of

Two lignin-degrading basidiomycetes, Stereum hirsutum and Heterobasidium insulare, were used to degrade bisphenol A (BPA) in culture, and the estrogenic activity of the degradation products was examined using MCF-7 cell proliferation assays (E-screen) and analysis of pS2 mRNA expression in MCF 7 cells. Both S. hirsutum and H. insulare showed high resistance to BPA 100 ppm, and their mycelial growth was fully completed within 8 d of incubation at 30 degrees C. It took 7 to 14 d to achieve complet

In this study, white rot fungus, Polyporus brumalis, was applied to degrade dibutyl phthalate (DBP), a major environmental pollutant. The degradation potential and resulting products were evaluated with HPLC and GC/MS. As DBP concentration increased to 250, 750, and 1,250 microM, the mycelial growth of P. brumalis was inhibited. However, growth was still observed in the 1,250 microM concentration. DBP was nearly eliminated from culture medium of P. brumalis within 12 days, with 50% of DBP adsorb

While deep learning (DL) has brought a revolution in the protein structure prediction field, still an important question remains how the revolution can be transferred to advances in structure-based drug discovery. Because the lessons from the recent GPCR dock challenge were inconclusive primarily due to the size of the dataset, in this work we further elaborated on 70 diverse GPCR complexes bound to either small molecules or peptides to investigate the best-practice modeling and docking strategi

Technologies to decipher cellular biology, such as bulk sequencing technologies and single-cell sequencing technologies, have greatly assisted novel findings in tumor biology. Recent findings in tumor biology suggest that tumors construct architectures that influence the underlying cancerous mechanisms. Increasing research has reported novel techniques to map the tissue in a spatial context or targeted sampling-based characterization and has introduced such technologies to solve oncology regardi

Technology for transforming a 2D pen drawing into a designed 3D structure enables highly accessible, rapid 3D fabrication.

This paper introduces consensus-based primal-dual methods for distributed online optimization where the time-varying system objective function $f_t(\mathbf{x})$ is given as the sum of local agents' objective functions, i.e., $f_t(\mathbf{x}) = \sum_i f_{i,t}(\mathbf{x}_i)$, and the system constraint function $\mathbf{g}(\mathbf{x})$ is given as the sum of local agents' constraint functions, i.e., $\mathbf{g}(\mathbf{x}) = \sum_i \mathbf{g}_i (\mathbf{x}_i) \preceq \mathbf{0}$. At each stage, eac

Earthwork is seemingly guesswork, but it requires a high level of accuracy and precise planning. Differences between earthwork design and finishing levels cause project delays and cost overrun due to the time-consuming nature of earthwork re-work. Therefore, error-free earthwork planning and design review is a key to the success of earthwork projects. This study utilized an integrated approach of an unmanned aerial vehicle (UAV)-based point cloud and BIM (Building Information Modeling) to verify

This paper introduces a decentralized primal-dual method for online distributed optimization involving global constraints. We employ a consensus-based framework and exploit the decomposability of the constraints in dual domain. At each stage, each agent commits to an adaptive decision pertaining only to the past and locally available information, and incurs a new cost function reflecting the change in the environment. We show that the algorithm achieves a regret of order O(√T) at any node with t