Search

The advantages coming from involving quantum systems in machine learning are still not fully clear. Here, the authors propose a software/hardware co-design framework towards quantum-friendly neural networks showing quantum advantage, representing data as either random variables or numbers in unitary matrices.

Abstract Higher-order tensors can represent scores in a rating system, frames in a video, and images of the same subject. In practice, the measurements are often highly quantized due to the sampling strategies or the quality of devices. Existing works on tensor recovery have focused on data losses and random noises. Only a few works consider tensor recovery from quantized measurements but are restricted to binary measurements. This paper, for the first time, addresses the problem of tensor recovery from multi-level quantized measurements by leveraging the low CANDECOMP/PARAFAC (CP) rank property. We study the recovery of both general low-rank tensors and tensors that have tensor singular value decomposition (TSVD) by solving nonconvex optimization problems. We provide the theoretical upper bounds of the recovery error, which diminish to zero when the sizes of dimensions increase to infinity. We further characterize the fundamental limit of any recovery algorithm and show that our recovery error is nearly order-wise optimal. A tensor-based alternating proximal gradient descent algorithm with a convergence guarantee and a TSVD-based projected gradient descent algorithm are proposed to solve the nonconvex problems. Our recovery methods can also handle data losses and do not necessarily need the information of the quantization rule. The methods are validated on synthetic data, image datasets, and music recommender datasets.

Abstract This paper develops a data collection and processing framework that achieves individual users’ data privacy and the operator’s information accuracy simultaneously. Data privacy is enhanced by adding noise and applying quantization to the data before transmission, and the privacy of an individual user is measured by information-theoretic analysis. This paper develops a data recovery and clustering method for the operator to extract features from the privacy-preserving, partially corrupted, and partially observed measurements of a large number of users. To prevent cyber intruders from accessing the data of many users, it also develops a decentralized algorithm such that multiple data owners can collaboratively recover and cluster the data without sharing the raw measurements directly. The recovery accuracy is characterized analytically and showed to be close to the fundamental limit of any recovery method. The proposed algorithm is proved to converge to a critical point from any initial point. The method is evaluated on recorded Irish smart meter data and UMass smart microgrid data.

With the society’s growing adoption of machine learning (ML) and deep learning (DL) for various intelligent solutions, it becomes increasingly imperative to standardize a common set of measures for ML/DL models with large scale open datasets under common development practices and resources so that people can benchmark and compare models’ quality and performance on a common ground. MLCommons has emerged recently as a driving force from both industry and academia to orchestrate such an effort. Despite its wide adoption as standardized benchmarks, MLCommons Inference has only included a limited number of ML/DL models (in fact seven models in total). This significantly limits the generality of MLCommons Inference’s benchmarking results because there are many more novel ML/DL models from the research community, solving a wide range of problems with different inputs and outputs modalities. To address such a limitation, we propose MLHarness, a scalable benchmarking harness system for MLCommons Inference with three distinctive features: (1) it codifies the standard benchmark process as defined by MLCommons Inference including the models, datasets, DL frameworks, and software and hardware systems; (2) it provides an easy and declarative approach for model developers to contribute their models and datasets to MLCommons Inference; and (3) it includes the support of a wide range of models with varying inputs/outputs modalities so that we can scalably benchmark these models across different datasets, frameworks, and hardware systems. This harness system is developed on top of the MLModelScope system, and will be open sourced to the community. Our experimental results demonstrate the superior flexibility and scalability of this harness system for MLCommons Inference benchmarking.

A 73-year-old woman was found to have a 1.7 cm axillary mass, for which a core needle biopsy was performed. The specimen revealed fragmented squamous epithelium surrounded by lymphoid tissue consistent with a squamous inclusion cyst in a lymph node, but a metastatic squamous cell carcinoma could not be excluded. Within one month, the lesion enlarged to 5 cm and was excised. Touch preparation cytology during intraoperative consultation displayed numerous single and sheets of atypical epithelioid cells with enlarged nuclei and occasional mitoses, suggesting a carcinoma. However, multinucleated giant cells and neutrophils in the background indicated reactive changes. We interpreted the touch preparation as atypical and recommended conservative surgical management. Permanent sections revealed a ruptured squamous inclusion cyst in a lymph node with extensive reactive changes. Retrospectively, the atypical epithelioid cells on touch preparation corresponded to reactive histiocytes. This is the first case report of a rapidly enlarging ruptured squamous inclusion cyst in an axillary lymph node following core needle biopsy. Our case demonstrates the diagnostic challenges related to a ruptured squamous inclusion cyst and serves to inform the readers to consider this lesion in the differential diagnosis for similar situations.