This paper presents a novel and lightweight hyperparameter optimization (HPO) method, MOdular FActorial Design (MOFA). MOFA pursues several rounds of HPO, where each round alternates between exploration of hyperparameter space by factorial design and
exploitation of evaluation results by factorial analysis. Each round first explores the configuration space by constructing a low-discrepancy set of hyperparameters that cover this space well while de-correlating hyperparameters, and then exploits evaluation results through factorial analysis that determines which hyperparameters should be further explored and which should become fixed in the next round. We prove that the inference of MOFA achieves higher confidence than other sampling schemes. Each individual round is highly parallelizable and hence offers major improvements of efficiency compared to model-based methods. Empirical results show that MOFA achieves better effectiveness and efficiency compared with state-of-the-art methods.
An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Existing methods are limited by the amount of parallel corpus. Can we build a system to fully utilize signals in a parallel ST c
orpus? We are inspired by human understanding system which is composed of auditory perception and cognitive processing. In this paper, we propose Listen-Understand-Translate, (LUT), a unified framework with triple supervision signals to decouple the end-to-end speech-to-text translation task. LUT is able to guide the acoustic encoder to extract as much information from the auditory input. In addition, LUT utilizes a pre-trained BERT model to enforce the upper encoder to produce as much semantic information as possible, without extra data. We perform experiments on a diverse set of speech translation benchmarks, including Librispeech English-French, IWSLT English-German and TED English-Chinese. Our results demonstrate LUT achieves the state-of-the-art performance, outperforming previous methods. The code is available at https://github.com/dqqcasia/st.
Synthesizing realistic medical images provides a feasible solution to the shortage of training data in deep learning based medical image recognition systems. However, the quality control of synthetic images for data augmentation purposes is under-inv
estigated, and some of the generated images are not realistic and may contain misleading features that distort data distribution when mixed with real images. Thus, the effectiveness of those synthetic images in medical image recognition systems cannot be guaranteed when they are being added randomly without quality assurance. In this work, we propose a reinforcement learning (RL) based synthetic sample selection method that learns to choose synthetic images containing reliable and informative features. A transformer based controller is trained via proximal policy optimization (PPO) using the validation classification accuracy as the reward. The selected images are mixed with the original training data for improved training of image recognition systems. To validate our method, we take the pathology image recognition as an example and conduct extensive experiments on two histopathology image datasets. In experiments on a cervical dataset and a lymph node dataset, the image classification performance is improved by 8.1% and 2.3%, respectively, when utilizing high-quality synthetic images selected by our RL framework. Our proposed synthetic sample selection method is general and has great potential to boost the performance of various medical image recognition systems given limited annotation.
We consider a homogeneous mixture of bosons and polarized fermions. We find that long-range and attractive fermion-mediated interactions between bosons have dramatic effects on the properties of the bosons. We construct the phase diagram spanned by b
oson-fermion mass ratio and boson-fermion scattering parameter. It consists of stable region of mixing and unstable region toward phase separation. In stable mixing phase, the collective long-wavelength excitations can either be well-behaved with infinite lifetime or be finite in lifetime suffered from the Landau damping. We examine the effects of the induced interaction on the properties of weakly interacting bosons. It turns out that the induced interaction not only enhances the repulsion between the bosons against collapse but also enhances the stability of the superfluid state by suppressing quantum depletion.
How to generate descriptions from structured data organized in tables? Existing approaches using neural encoder-decoder models often suffer from lacking diversity. We claim that an open set of templates is crucial for enriching the phrase constructio
ns and realizing varied generations. Learning such templates is prohibitive since it often requires a large paired <table, description> corpus, which is seldom available. This paper explores the problem of automatically learning reusable templates from paired and non-paired data. We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables. Our contributions include: a) we carefully devise a specific model architecture and losses to explicitly disentangle text template and semantic content information, in the latent spaces, and b)we utilize both small parallel data and large raw text without aligned tables to enrich the template learning. Experiments on datasets from a variety of different domains show that VTM is able to generate more diversely while keeping a good fluency and quality.
Supervised training of an automated medical image analysis system often requires a large amount of expert annotations that are hard to collect. Moreover, the proportions of data available across different classes may be highly imbalanced for rare dis
eases. To mitigate these issues, we investigate a novel data augmentation pipeline that selectively adds new synthetic images generated by conditional Adversarial Networks (cGANs), rather than extending directly the training set with synthetic images. The selection mechanisms that we introduce to the synthetic augmentation pipeline are motivated by the observation that, although cGAN-generated images can be visually appealing, they are not guaranteed to contain essential features for classification performance improvement. By selecting synthetic images based on the confidence of their assigned labels and their feature similarity to real labeled images, our framework provides quality assurance to synthetic augmentation by ensuring that adding the selected synthetic images to the training set will improve performance. We evaluate our model on a medical histopathology dataset, and two natural image classification benchmarks, CIFAR10 and SVHN. Results on these datasets show significant and consistent improvements in classification performance (with 6.8%, 3.9%, 1.6% higher accuracy, respectively) by leveraging cGAN generated images with selective augmentation.
We perform an in-plane optical spectroscopy measurement on high quality FeSe single crystals grown by a vapor transport technique. Below the structural transition at $T_{rm s}sim$90 K, the reflectivity spectrum clearly shows a gradual suppression aro
und 400 cm$^{-1}$ and the conductivity spectrum shows a peak at higher frequency. The energy scale of this gap-like feature is comparable to the width of the band splitting observed by ARPES. The low-frequency conductivity consists of two Drude components and the overall plasma frequency is smaller than that of the FeAs based compounds, suggesting a lower carrier density or stronger correlation effect. The plasma frequency becomes even smaller below $T_{rm s}$ which agrees with the very small Fermi energy estimated by other experiments. Similar to iron pnictides, a clear temperature-induced spectral weight transfer is observed for FeSe, being indicative of strong correlation effect.
