Exponential Error Convergence in Data Classification with Optimized Random Features: Acceleration by Quantum Machine Learning

Random features are a central technique for scalable learning algorithms based on kernel methods. A recent work has shown that an algorithm for machine learning by quantum computer, quantum machine learning (QML), can exponentially speed up sampling of optimized random features, even without imposing restrictive assumptions on sparsity and low-rankness of matrices that had limited applicability of conventional QML algorithms; this QML algorithm makes it possible to significantly reduce and provably minimize the required number of features for regression tasks. However, a major interest in the field of QML is how widely the advantages of quantum computation can be exploited, not only in the regression tasks. We here construct a QML algorithm for a classification task accelerated by the optimized random features. We prove that the QML algorithm for sampling optimized random features, combined with stochastic gradient descent (SGD), can achieve state-of-the-art exponential convergence speed of reducing classification error in a classification task under a low-noise condition; at the same time, our algorithm with optimized random features can take advantage of the significant reduction of the required number of features so as to accelerate each iteration in the SGD and evaluation of the classifier obtained from our algorithm. These results discover a promising application of QML to significant acceleration of the leading classification algorithm based on kernel methods, without ruining its applicability to a practical class of data sets and the exponential error-convergence speed.

Stimuli-Sensitive Hawkes Processes for Personalized Student Procrastination Modeling

Student procrastination and cramming for deadlines are major challenges in online learning environments, with negative educational and well-being side effects. Modeling student activities in continuous time and predicting their next study time are important problems that can help in creating personalized timely interventions to mitigate these challenges. However, previous attempts on dynamic modeling of student procrastination suffer from major issues: they are unable to predict the next activity times, cannot deal with missing activity history, are not personalized, and disregard important course properties, such as assignment deadlines, that are essential in explaining the cramming behavior. To resolve these problems, we introduce a new personalized stimuli-sensitive Hawkes process model (SSHP), by jointly modeling all student-assignment pairs and utilizing their similarities, to predict students' next activity times even when there are no historical observations. Unlike regular point processes that assume a constant external triggering effect from the environment, we model three dynamic types of external stimuli, according to assignment availabilities, assignment deadlines, and each student's time management habits. Our experiments on two synthetic datasets and two real-world datasets show a superior performance of future activity prediction, comparing with state-of-the-art models. Moreover, we show that our model achieves a flexible and accurate parameterization of activity intensities in students.

A Spiking Neural Network for Image Segmentation

We seek to investigate the scalability of neuromorphic computing for computer vision, with the objective of replicating non-neuromorphic performance on computer vision tasks while reducing power consumption. We convert the deep Artificial Neural Network (ANN) architecture U-Net to a Spiking Neural Network (SNN) architecture using the Nengo framework. Both rate-based and spike-based models are trained and optimized for benchmarking performance and power, using a modified version of the ISBI 2D EM Segmentation dataset consisting of microscope images of cells. We propose a partitioning method to optimize inter-chip communication to improve speed and energy efficiency when deploying multi-chip networks on the Loihi neuromorphic chip. We explore the advantages of regularizing firing rates of Loihi neurons for converting ANN to SNN with minimum accuracy loss and optimized energy consumption. We propose a percentile based regularization loss function to limit the spiking rate of the neuron between a desired range. The SNN is converted directly from the corresponding ANN, and demonstrates similar semantic segmentation as the ANN using the same number of neurons and weights. However, the neuromorphic implementation on the Intel Loihi neuromorphic chip is over 2x more energy-efficient than conventional hardware (CPU, GPU) when running online (one image at a time). These power improvements are achieved without sacrificing the task performance accuracy of the network, and when all weights (Loihi, CPU, and GPU networks) are quantized to 8 bits.

MLComp: A Methodology for Machine Learning-based Performance Estimation and Adaptive Selection of Pareto-Optimal Compiler Optimization Sequences

Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must be optimized for multiple objectives simultaneously, namely reduced energy consumption, execution time, and code size. Compilers offer optimization phases to improve these metrics. However, proper selection and ordering of them depends on multiple factors and typically requires expert knowledge. State-of-the-art optimizers facilitate different platforms and applications case by case, and they are limited by optimizing one metric at a time, as well as requiring a time-consuming adaptation for different targets through dynamic profiling. To address these problems, we propose the novel MLComp methodology, in which optimization phases are sequenced by a Reinforcement Learning-based policy. Training of the policy is supported by Machine Learning-based analytical models for quick performance estimation, thereby drastically reducing the time spent for dynamic profiling. In our framework, different Machine Learning models are automatically tested to choose the best-fitting one. The trained Performance Estimator model is leveraged to efficiently devise Reinforcement Learning-based multi-objective policies for creating quasi-optimal phase sequences. Compared to state-of-the-art estimation models, our Performance Estimator model achieves lower relative error (<2%) with up to 50x faster training time over multiple platforms and application domains. Our Phase Selection Policy improves execution time and energy consumption of a given code by up to 12% and 6%, respectively. The Performance Estimator and the Phase Selection Policy can be trained efficiently for any target platform and application domain.

Deep Animation Video Interpolation in the Wild

In the animation industry, cartoon videos are usually produced at low frame rate since hand drawing of such frames is costly and time-consuming. Therefore, it is desirable to develop computational models that can automatically interpolate the in-between animation frames. However, existing video interpolation methods fail to produce satisfying results on animation data. Compared to natural videos, animation videos possess two unique characteristics that make frame interpolation difficult: 1) cartoons comprise lines and smooth color pieces. The smooth areas lack textures and make it difficult to estimate accurate motions on animation videos. 2) cartoons express stories via exaggeration. Some of the motions are non-linear and extremely large. In this work, we formally define and study the animation video interpolation problem for the first time. To address the aforementioned challenges, we propose an effective framework, AnimeInterp, with two dedicated modules in a coarse-to-fine manner. Specifically, 1) Segment-Guided Matching resolves the "lack of textures" challenge by exploiting global matching among color pieces that are piece-wise coherent. 2) Recurrent Flow Refinement resolves the "non-linear and extremely large motion" challenge by recurrent predictions using a transformer-like architecture. To facilitate comprehensive training and evaluations, we build a large-scale animation triplet dataset, ATD-12K, which comprises 12,000 triplets with rich annotations. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art interpolation methods for animation videos. Notably, AnimeInterp shows favorable perceptual quality and robustness for animation scenarios in the wild. The proposed dataset and code are available at https://github.com/lisiyao21/AnimeInterp/.

Score-based Generative Modeling in Latent Space

Score-based generative models (SGMs) have recently demonstrated impressive results in terms of both sample quality and distribution coverage. However, they are usually applied directly in data space and often require thousands of network evaluations for sampling. Here, we propose the Latent Score-based Generative Model (LSGM), a novel approach that trains SGMs in a latent space, relying on the variational autoencoder framework. Moving from data to latent space allows us to train more expressive generative models, apply SGMs to non-continuous data, and learn smoother SGMs in a smaller space, resulting in fewer network evaluations and faster sampling. To enable training LSGMs end-to-end in a scalable and stable manner, we (i) introduce a new score-matching objective suitable to the LSGM setting, (ii) propose a novel parameterization of the score function that allows SGM to focus on the mismatch of the target distribution with respect to a simple Normal one, and (iii) analytically derive multiple techniques for variance reduction of the training objective. LSGM obtains a state-of-the-art FID score of 2.10 on CIFAR-10, outperforming all existing generative results on this dataset. On CelebA-HQ-256, LSGM is on a par with previous SGMs in sample quality while outperforming them in sampling time by two orders of magnitude. In modeling binary images, LSGM achieves state-of-the-art likelihood on the binarized OMNIGLOT dataset.

FetReg: Placental Vessel Segmentation and Registration in Fetoscopy Challenge Dataset

Fetoscopy laser photocoagulation is a widely used procedure for the treatment of Twin-to-Twin Transfusion Syndrome (TTTS), that occur in mono-chorionic multiple pregnancies due to placental vascular anastomoses. This procedure is particularly challenging due to limited field of view, poor manoeuvrability of the fetoscope, poor visibility due to fluid turbidity, variability in light source, and unusual position of the placenta. This may lead to increased procedural time and incomplete ablation, resulting in persistent TTTS. Computer-assisted intervention may help overcome these challenges by expanding the fetoscopic field of view through video mosaicking and providing better visualization of the vessel network. However, the research and development in this domain remain limited due to unavailability of high-quality data to encode the intra- and inter-procedure variability. Through the Fetoscopic Placental Vessel Segmentation and Registration (FetReg) challenge, we present a large-scale multi-centre dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms for the fetal environment with a focus on creating drift-free mosaics from long duration fetoscopy videos. In this paper, we provide an overview of the FetReg dataset, challenge tasks, evaluation metrics and baseline methods for both segmentation and registration. Baseline methods results on the FetReg dataset shows that our dataset poses interesting challenges, which can be modelled and competed for through our crowd-sourcing initiative of the FetReg challenge.

Annotation Curricula to Implicitly Train Non-Expert Annotators

Annotation studies often require annotators to familiarize themselves with the task, its annotation scheme, and the data domain. This can be overwhelming in the beginning, mentally taxing, and induce errors into the resulting annotations; especially in citizen science or crowd sourcing scenarios where domain expertise is not required and only annotation guidelines are provided. To alleviate these issues, we propose annotation curricula, a novel approach to implicitly train annotators. Our goal is to gradually introduce annotators into the task by ordering instances that are annotated according to a learning curriculum. To do so, we first formalize annotation curricula for sentence- and paragraph-level annotation tasks, define an ordering strategy, and identify well-performing heuristics and interactively trained models on three existing English datasets. We then conduct a user study with 40 voluntary participants who are asked to identify the most fitting misconception for English tweets about the Covid-19 pandemic. Our results show that using a simple heuristic to order instances can already significantly reduce the total annotation time while preserving a high annotation quality. Annotation curricula thus can provide a novel way to improve data collection. To facilitate future research, we further share our code and data consisting of 2,400 annotations.

Reinforcement learning for Admission Control in 5G Wireless Networks

The key challenge in admission control in wireless networks is to strike an optimal trade-off between the blocking probability for new requests while minimizing the dropping probability of ongoing requests. We consider two approaches for solving the admission control problem: i) the typically adopted threshold policy and ii) our proposed policy relying on reinforcement learning with neural networks. Extensive simulation experiments are conducted to analyze the performance of both policies. The results show that the reinforcement learning policy outperforms the threshold-based policies in the scenario with heterogeneous time-varying arrival rates and multiple user equipment types, proving its applicability in realistic wireless network scenarios.

Many-Speakers Single Channel Speech Separation with Optimal Permutation Training

Single channel speech separation has experienced great progress in the last few years. However, training neural speech separation for a large number of speakers (e.g., more than 10 speakers) is out of reach for the current methods, which rely on the Permutation Invariant Loss (PIT). In this work, we present a permutation invariant training that employs the Hungarian algorithm in order to train with an $O(C^3)$ time complexity, where $C$ is the number of speakers, in comparison to $O(C!)$ of PIT based methods. Furthermore, we present a modified architecture that can handle the increased number of speakers. Our approach separates up to $20$ speakers and improves the previous results for large $C$ by a wide margin.