arXiv subjects

Bo Lyu

Publications and source records attributed to Bo Lyu.

7 recordsLinked to original sources

arXiv2025

OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search

Neural architecture search (NAS) is a hard computationally expensive optimization problem with a discrete, vast, and spiky search space. One of the key research efforts dedicated to this space focuses on accelerating NAS via certain proxy evaluations of neural architectures. Different from the prevalent predictor-based methods using surrogate models and differentiable architecture search via supernetworks, we propose an optimization proxy to streamline the NAS as an end-to-end optimization framework, named OptiProxy-NAS. In particular, using a proxy representation, the NAS space is reformulated to be continuous, differentiable, and smooth. Thereby, any differentiable optimization method can be applied to the gradient-based search of the relaxed architecture parameters. Our comprehensive experiments on $12$ NAS tasks of $4$ search spaces across three different domains including computer vision, natural language processing, and resource-constrained NAS fully demonstrate the superior search results and efficiency. Further experiments on low-fidelity scenarios verify the flexibility.

cs.LG↗

arXiv2024

Deep Mamba Multi-modal Learning

Inspired by the excellent performance of Mamba networks, we propose a novel Deep Mamba Multi-modal Learning (DMML). It can be used to achieve the fusion of multi-modal features. We apply DMML to the field of multimedia retrieval and propose an innovative Deep Mamba Multi-modal Hashing (DMMH) method. It combines the advantages of algorithm accuracy and inference speed. We validated the effectiveness of DMMH on three public datasets and achieved state-of-the-art results.

cs.MM↗

arXiv2022

First Identification of New X-Ray Spectra of Mo39+, Mo40+, W43+, W44+ and W45+ on EAST

New high-resolution x-ray spectra of Mo39+, Mo40+, W43+, W44+ and W45+ have been carefully confirmed for the first time by use of the x-ray imaging crystal spectrometer (XCS) in Experimental Advanced Superconducting Tokamak (EAST) under various combined auxiliary heating plasmas conditions. Wavelength of these new x-ray spectra is ranged from 3.895 {\AA} to 3.986 {\AA}. When core electron temperature (Te0) reaches 6.0 keV, Mo39+ and Mo40+ lines of 3.9727, 3.9294 and 3.9480 {\AA} can be effectively detected on XCS for EAST; meanwhile, line-integrated brightness of these spectral lines of Mo39+ and Mo40+ is very considerable when electron temperature reaches 12.9 keV. Multi-components spectral lines for W43+, W44+ and W45+ have also been identified when Te0 reaches 6 keV. Parts of spectral lines, such as Zn-1, Cu-2, Cu-4a, Cu-4d and Cu-5 lines of tungsten, are first observed experimentally. When electron temperature reaches 12.9 keV, line-integrated intensity for part of these spectral lines of W43+, W44+ and W45+ are considerable. These experimental results and theoretical predictions from FAC and FLYCHK codes are in good general agreement. These new spectral lines, obtained on XCS for EAST, are vital for deeply uncovering the mechanisms of ion and electron thermal, high-Z impurity and momentum (anomalous) transport to achieve the advanced steady-state operation scenarios for ITER and CFETR.

physics.plasm-ph↗

arXiv2021

Robust Adaptive Safety-Critical Control for Unknown Systems with Finite-Time Element-Wise Parameter Estimation

Safety is always one of the most critical principles for a system to be controlled. This paper investigates a safety-critical control scheme for unknown structured systems by using the control barrier function (CBF) method. Benefited from the dynamic regressor extension and mixing (DREM), an extended element-wise parameter identification law is utilized to dismiss the uncertainty. On the one hand, it is shown that the proposed control scheme can always guarantee the safety in the identification process with noised signal injection excitation, which was not considered in the previous study. On the other hand, the element-wise estimation process in DREM can minimize conservatism of the safe adaptive process compared to other existing adaptive CBF algorithms. The stability as well as the forward invariance of the presented safe control-estimation scheme is proved. Furthermore, the robustness of the scheme under bounded disturbances is analyzed, where a robust CBF with modest conditions is used to ensure safety. The framework is illustrated by simulations on adaptive cruise control, where the slope resistance of the following vehicle is robustly estimated in finite time against small disturbances and the potential crash risk is avoided by the proposed safe control scheme.

eess.SY↗

arXiv2021

AutoGMap: Learning to Map Large-scale Sparse Graphs on Memristive Crossbars

The sparse representation of graphs has shown great potential for accelerating the computation of graph applications (e.g., Social Networks, Knowledge Graphs) on traditional computing architectures (CPU, GPU, or TPU). But the exploration of large-scale sparse graph computing on processing-in-memory (PIM) platforms (typically with memristive crossbars) is still in its infancy. To implement the computation or storage of large-scale or batch graphs on memristive crossbars, a natural assumption is that a large-scale crossbar is demanded, but with low utilization. Some recent works question this assumption, to avoid the waste of storage and computational resource, the fixed-size or progressively scheduled ''block partition'' schemes are proposed. However, these methods are coarse-grained or static, and are not effectively sparsity-aware. This work proposes the dynamic sparsity-aware mapping scheme generating method that models the problem with a sequential decision-making model, and optimizes it by reinforcement learning (RL) algorithm (REINFORCE). Our generating model (LSTM, combined with the dynamic-fill scheme) generates remarkable mapping performance on a small-scale graph/matrix data (complete mapping costs 43% area of the original matrix) and two large-scale matrix data (costing 22.5% area on qh882 and 17.1% area on qh1484). Our method may be extended to sparse graph computing on other PIM architectures, not limited to the memristive device-based platforms.

cs.LG↗

arXiv2021

TND-NAS: Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework

Differentiable architecture search has gradually become the mainstream research topic in the field of Neural Architecture Search (NAS) for its high efficiency compared with the early NAS methods. Recent differentiable NAS also aims at further improving the search performance and reducing the GPU-memory consumption. However, these methods are no longer naturally capable of tackling the non-differentiable objectives, e.g., energy, resource-constrained efficiency, and other metrics, let alone the multi-objective search demands. Researches in the multi-objective NAS field target this but requires vast computational resources cause of the sole optimization of each candidate architecture. In light of this discrepancy, we propose the TND-NAS, which is with the merits of the high efficiency in differentiable NAS framework and the compatibility among non-differentiable metrics in Multi-objective NAS. Under the differentiable NAS framework, with the continuous relaxation of the search space, TND-NAS has the architecture parameters been optimized in discrete space, while resorting to the progressive search space shrinking by architecture parameters. Our representative experiment takes two objectives (Parameters, Accuracy) as an example, we achieve a series of high-performance compact architectures on CIFAR10 (1.09M/3.3%, 2.4M/2.95%, 9.57M/2.54%) and CIFAR100 (2.46M/18.3%, 5.46/16.73%, 12.88/15.20%) datasets. Favorably, compared with other multi-objective NAS methods, TND-NAS is less time-consuming (1.3 GPU-days on NVIDIA 1080Ti, 1/6 of that in NSGA-Net), and can be conveniently adapted to real-world NAS scenarios (resource-constrained, platform-specialized).

cs.LG↗

arXiv2014

Investigation of toroidal acceleration and potential acceleration forces in EAST and J-TEXT plasmas

In order to produce intrinsic rotation, bulk plasmas must be collectively accelerated by the net force exerted on them, which results from both driving and damping forces. So, to study the possible mechanisms of intrinsic rotation generation, it is only needed to understand characteristics of driving and damping terms because the toroidal driving and damping forces induce net acceleration which generates intrinsic rotation. Experiments were performed on EAST and J-TEXT for ohmic plasmas with net counter- and co-current toroidal acceleration generated by density ramping up and ramping down. Additionally on EAST, net co-current toroidal acceleration was also formed by LHCD or ICRF. For the current experimental results, toroidal acceleration was between - 50 km/s^2 in counter-current direction and 70 km/s^2 in co-current direction. According to toroidal momentum equation, toroidal electric field (E\-(\g(f))), electron-ion toroidal friction, and toroidal viscous force etc. may play roles in the evolution of toroidal rotation. To evaluate contribution of each term, we first analyze characteristics of E\-(\g(f)). E\-(\g(f)) is one of the co-current toroidal forces that acts on the plasma as a whole and persists for the entire discharge period. It was shown to drive the co-current toroidal acceleration at a magnitude of 10^3 km/s^2, which was much larger than the experimental toroidal acceleration observed on EAST and J-TEXT. So E\-(\g(f)) is one of co-current forces producing cocurrent intrinsic toroidal acceleration and rotation. Meanwhile, it indicates that there must be a strong counter-current toroidal acceleration resulting from counter-current toroidal forces. Electron-ion toroidal friction is one of the counter-current toroidal forces because global electrons move in the counter-current direction in order to produce a toroidal plasma current.

physics.plasm-ph↗