arXiv subjects

Yuwen Chen

Publications and source records attributed to Yuwen Chen.

45 records · Page 3Linked to original sources

arXiv2023

High Efficiency Inference Accelerating Algorithm for NOMA-based Mobile Edge Computing

Splitting the inference model between device, edge server, and cloud can improve the performance of EI greatly. Additionally, the non-orthogonal multiple access (NOMA), which is the key supporting technologies of B5G/6G, can achieve massive connections and high spectrum efficiency. Motivated by the benefits of NOMA, integrating NOMA with model split in MEC to reduce the inference latency further becomes attractive. However, the NOMA based communication during split inference has not been properly considered in previous works. Therefore, in this paper, we integrate the NOMA into split inference in MEC, and propose the effective communication and computing resource allocation algorithm to accelerate the model inference at edge. Specifically, when the mobile user has a large model inference task needed to be calculated in the NOMA-based MEC, it will take the energy consumption of both device and edge server and the inference latency into account to find the optimal model split strategy, subchannel allocation strategy (uplink and downlink), and transmission power allocation strategy (uplink and downlink). Since the minimum inference delay and energy consumption cannot be satisfied simultaneously, and the variables of subchannel allocation and model split are discrete, the gradient descent (GD) algorithm is adopted to find the optimal tradeoff between them. Moreover, the loop iteration GD approach (Li-GD) is proposed to reduce the complexity of GD algorithm that caused by the parameter discrete. Additionally, the properties of the proposed algorithm are also investigated, which demonstrate the effectiveness of the proposed algorithms.

cs.DC↗

arXiv2023

MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains

Medical imaging data is often siloed within hospitals, limiting the amount of data available for specialized model development. With limited in-domain data, one might hope to leverage larger datasets from related domains. In this paper, we analyze the benefit of transferring self-supervised contrastive representations from moment contrast (MoCo) pretraining on out-of-distribution data to settings with limited data. We consider two X-ray datasets which image different parts of the body, and compare transferring from each other to transferring from ImageNet. We find that depending on quantity of labeled and unlabeled data, contrastive pretraining on larger out-of-distribution datasets can perform nearly as well or better than MoCo pretraining in-domain, and pretraining on related domains leads to higher performance than if one were to use the ImageNet pretrained weights. Finally, we provide a preliminary way of quantifying similarity between datasets.

cs.CV↗

arXiv2023

Evaluating Model Performance in Medical Datasets Over Time

Machine learning (ML) models deployed in healthcare systems must face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, splitting datasets according to patients sampled randomly throughout the entire study time period. This work proposes the Evaluation on Medical Datasets Over Time (EMDOT) framework, which evaluates the performance of a model class across time. Inspired by the concept of backtesting, EMDOT simulates possible training procedures that practitioners might have been able to execute at each point in time and evaluates the resulting models on all future time points. Evaluating both linear and more complex models on six distinct medical data sources (tabular and imaging), we show how depending on the dataset, using all historical data may be ideal in many cases, whereas using a window of the most recent data could be advantageous in others. In datasets where models suffer from sudden degradations in performance, we investigate plausible explanations for these shocks. We release the EMDOT package to help facilitate further works in deployment-oriented evaluation over time.

cs.LG↗

arXiv2023

An Efficient IPM Implementation for A Class of Nonsymmetric Cones

We present an efficient implementation of interior point methods for a family of nonsymmetric cones, including generalized power cones, power mean cones and relative entropy cones, by exploiting underlying low-rank and sparse properties of Hessians of homogeneous self-concordant barrier functions. We prove that the augmented linear system in our interior point method is sparse and quasi-definite, enabling the use of sparse LDL factorization with a dual scaling strategy for nonsymmetric cones. Numerical results show that our proposed implementation for nonsymmetric cones performs much faster than the state-of-art solvers for spare problems and scales well for large problems.

math.OC↗

arXiv2023

WeLM: A Well-Read Pre-trained Language Model for Chinese

Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks. In this work, we present WeLM: a well-read pre-trained language model for Chinese that is able to seamlessly perform different types of tasks with zero or few-shot demonstrations. WeLM is trained with 10B parameters by "reading" a curated high-quality corpus covering a wide range of topics. We show that WeLM is equipped with broad knowledge on various domains and languages. On 18 monolingual (Chinese) tasks, WeLM can significantly outperform existing pre-trained models with similar sizes and match the performance of models up to 25 times larger. WeLM also exhibits strong capabilities in multi-lingual and code-switching understanding, outperforming existing multilingual language models pre-trained on 30 languages. Furthermore, We collected human-written prompts for a large set of supervised datasets in Chinese and fine-tuned WeLM with multi-prompted training. The resulting model can attain strong generalization on unseen types of tasks and outperform the unsupervised WeLM in zero-shot learning. Finally, we demonstrate that WeLM has basic skills at explaining and calibrating the decisions from itself, which can be promising directions for future research. Our models can be applied from https://welm.weixin.qq.com/docs/api/.

cs.CL↗

arXiv2023

A Unified Early Termination Technique for Primal-dual Algorithms in Mixed Integer Conic Programming

We propose an early termination technique for mixed integer conic programming for use within branch-and-bound based solvers. Our approach generalizes previous early termination results for ADMM-based solvers to a broader class of primal-dual algorithms, including both operator splitting methods and interior point methods. The complexity for checking early termination is $O(n)$ for each termination check assuming a bounded problem domain. We show that this domain restriction can be relaxed for problems whose data satisfies a simple rank condition, in which case each check requires an $O(n^2)$ solve using a linear system that must be factored only once at the root node. We further show how this approach can be used in hybrid model predictive control as long as system inputs are bounded. Numerical results show that our method leads to a moderate reduction in the total iterations required for branch-and-bound conic solvers with interior-point based subsolvers.

math.OC↗

arXiv2023

Burer-Monteiro ADMM for Large-scale SDPs

We propose a bilinear decomposition for the Burer-Monteiro method and combine it with the standard Alternating Direction Method of Multipliers algorithm for semidefinite programming. Bilinear decomposition reduces the degree of the augmented Lagrangian from four to two, which makes each of the subproblems a quadratic programming and hence computationally efficient. Our approach is able to solve a class of large-scale SDPs with diagonal constraints. We prove that our ADMM algorithm converges globally to a first-order stationary point, and show by exploiting the negative curvature that the algorithm converges to a point within $O(1-1/r)$ of the optimal objective value. Additionally, the proximal variant of the algorithm can solve block-diagonally constrained SDPs with global convergence to a first-order stationary point. Numerical results show that both our ADMM algorithm and the proximal variant outperform the state-of-art Riemannian manifold algorithms and can reach the global optimum empirically.

math.OC↗

arXiv2022

Model Evaluation in Medical Datasets Over Time

Machine learning models deployed in healthcare systems face data drawn from continually evolving environments. However, researchers proposing such models typically evaluate them in a time-agnostic manner, with train and test splits sampling patients throughout the entire study period. We introduce the Evaluation on Medical Datasets Over Time (EMDOT) framework and Python package, which evaluates the performance of a model class over time. Across five medical datasets and a variety of models, we compare two training strategies: (1) using all historical data, and (2) using a window of the most recent data. We note changes in performance over time, and identify possible explanations for these shocks.

cs.LG↗

arXiv2020

An Accelerated DFO Algorithm for Finite-sum Convex Functions

Derivative-free optimization (DFO) has recently gained a lot of momentum in machine learning, spawning interest in the community to design faster methods for problems where gradients are not accessible. While some attention has been given to the concept of acceleration in the DFO literature, existing stochastic algorithms for objective functions with a finite-sum structure have not been shown theoretically to achieve an accelerated rate of convergence. Algorithms that use acceleration in such a setting are prone to instabilities, making it difficult to reach convergence. In this work, we exploit the finite-sum structure of the objective in order to design a variance-reduced DFO algorithm that provably yields acceleration. We prove rates of convergence for both smooth convex and strongly-convex finite-sum objective functions. Finally, we validate our theoretical results empirically on several tasks and datasets.

math.OC↗