arXiv subjects

Han Bao

Publications and source records attributed to Han Bao.

111 records · Page 7Linked to original sources

arXiv2018

Classification from Pairwise Similarity and Unlabeled Data

Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high. To overcome this problem, we propose a new weakly-supervised learning setting where only similar (S) data pairs (two examples belong to the same class) and unlabeled (U) data points are needed instead of fully labeled data, which is called SU classification. We show that an unbiased estimator of the classification risk can be obtained only from SU data, and the estimation error of its empirical risk minimizer achieves the optimal parametric convergence rate. Finally, we demonstrate the effectiveness of the proposed method through experiments.

cs.LG↗

arXiv2018

Convex Formulation of Multiple Instance Learning from Positive and Unlabeled Bags

Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels are available. MIL has a variety of applications such as content-based image retrieval, text categorization and medical diagnosis. Most of the previous work for MIL assume that the training bags are fully labeled. However, it is often difficult to obtain an enough number of labeled bags in practical situations, while many unlabeled bags are available. A learning framework called PU learning (positive and unlabeled learning) can address this problem. In this paper, we propose a convex PU learning method to solve an MIL problem. We experimentally show that the proposed method achieves better performance with significantly lower computational costs than an existing method for PU-MIL.

cs.LG↗

arXiv2016

Two-axis-twisting spin squeezing by multi-pass quantum erasure

Many-body entangled states are key elements in quantum information science and quantum metrology. One important problem in establishing a high degree of many-body entanglement using optical techniques is the leakage of the system information via the light that creates such entanglement. We propose an all-optical interference-based approach to erase this information. Unwanted atom-light entanglement can be removed by destructive interference of three or more successive atom-light interactions, with only the desired effective atom-atom interaction left. This quantum erasure protocol allows implementation of Heisenberg-limited spin squeezing using coherent light and a cold or warm atomic ensemble. Calculations show that significant improvement in the squeezing exceeding 10 dB is obtained compared to previous methods, and substantial spin squeezing is attainable even under moderate experimental conditions. Our method enables the efficient creation of many-body entangled states with simple setups, and thus is promising for advancing technologies in quantum metrology and quantum information processing.

quant-ph↗