We propose a novel pitch estimation technique called DeepF0, which leverages the available annotated data to directly learns from the raw audio in a data-driven manner. F0 estimation is important in various speech processing and music information retrieval applications. Existing deep learning models for pitch estimations have relatively limited learning capabilities due to their shallow receptive field. The proposed model addresses this issue by extending the receptive field of a network by introducing the dilated convolutional blocks into the network. The dilation factor increases the network receptive field exponentially without increasing the parameters of the model exponentially. To make the training process more efficient and faster, DeepF0 is augmented with residual blocks with residual connections. Our empirical evaluation demonstrates that the proposed model outperforms the baselines in terms of raw pitch accuracy and raw chroma accuracy even using 77.4% fewer network parameters. We also show that our model can capture reasonably well pitch estimation even under the various levels of accompaniment noise.

Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built. This is particularly challenging when applying large Transformer language models to tactic prediction, because the scaling of performance with respect to model size is quickly disrupted in the data-scarce, easily-overfitted regime. We propose PACT ({\bf P}roof {\bf A}rtifact {\bf C}o-{\bf T}raining), a general methodology for extracting abundant self-supervised data from kernel-level proof terms for co-training alongside the usual tactic prediction objective. We apply this methodology to Lean, an interactive proof assistant which hosts some of the most sophisticated formalized mathematics to date. We instrument Lean with a neural theorem prover driven by a Transformer language model and show that PACT improves theorem proving success rate on a held-out suite of test theorems from 32\% to 48\%.

To enable an ethical and legal use of machine learning algorithms, they must both be fair and protect the privacy of those whose data are being used. However, implementing privacy and fairness constraints might come at the cost of utility (Jayaraman & Evans, 2019; Gong et al., 2020). This paper investigates the privacy-utility-fairness trade-off in neural networks by comparing a Simple (S-NN), a Fair (F-NN), a Differentially Private (DP-NN), and a Differentially Private and Fair Neural Network (DPF-NN) to evaluate differences in performance on metrics for privacy (epsilon, delta), fairness (risk difference), and utility (accuracy). In the scenario with the highest considered privacy guarantees (epsilon = 0.1, delta = 0.00001), the DPF-NN was found to achieve better risk difference than all the other neural networks with only a marginally lower accuracy than the S-NN and DP-NN. This model is considered fair as it achieved a risk difference below the strict (0.05) and lenient (0.1) thresholds. However, while the accuracy of the proposed model improved on previous work from Xu, Yuan and Wu (2019), the risk difference was found to be worse.

Background. Forecasting the time of forthcoming pandemic reduces the impact of diseases by taking precautionary steps such as public health messaging and raising the consciousness of doctors. With the continuous and rapid increase in the cumulative incidence of COVID-19, statistical and outbreak prediction models including various machine learning (ML) models are being used by the research community to track and predict the trend of the epidemic, and also in developing appropriate strategies to combat and manage its spread. Methods. In this paper, we present a comparative analysis of various ML approaches including Support Vector Machine, Random Forest, K-Nearest Neighbor and Artificial Neural Network in predicting the COVID-19 outbreak in the epidemiological domain. We first apply the autoregressive distributed lag (ARDL) method to identify and model the short and long-run relationships of the time-series COVID-19 datasets. That is, we determine the lags between a response variable and its respective explanatory time series variables as independent variables. Then, the resulting significant variables concerning their lags are used in the regression model selected by the ARDL for predicting and forecasting the trend of the epidemic. Results. Statistical measures i.e., Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used for model accuracy. The values of MAPE for the best selected models for confirmed, recovered and deaths cases are 0.407, 0.094 and 0.124 respectively, which falls under the category of highly accurate forecasts. In addition, we computed fifteen days ahead forecast for the daily deaths, recover, and confirm patients and the cases fluctuated across time in all aspects. Besides, the results reveal the advantages of ML algorithms for supporting decision making of evolving short term policies.

Platforms that support online commentary, from social networks to news sites, are increasingly leveraging machine learning to assist their moderation efforts. But this process does not typically provide feedback to the author that would help them contribute according to the community guidelines. This is prohibitively time-consuming for human moderators to do, and computational approaches are still nascent. This work focuses on models that can help suggest rephrasings of toxic comments in a more civil manner. Inspired by recent progress in unpaired sequence-to-sequence tasks, a self-supervised learning model is introduced, called CAE-T5. CAE-T5 employs a pre-trained text-to-text transformer, which is fine tuned with a denoising and cyclic auto-encoder loss. Experimenting with the largest toxicity detection dataset to date (Civil Comments) our model generates sentences that are more fluent and better at preserving the initial content compared to earlier text style transfer systems which we compare with using several scoring systems and human evaluation.

Jump Point Search (JPS) is a well known symmetry-breaking algorithm that can substantially improve performance for grid-based optimal pathfinding. When the input grid is static further speedups can be obtained by combining JPS with goal bounding techniques such as Geometric Containers (instantiated as Bounding Boxes) and Compressed Path Databases. Two such methods, JPS+BB and Two-Oracle Path PlannING (Topping), are currently among the fastest known approaches for computing shortest paths on grids. The principal drawback for these algorithms is the overhead costs: each one requires an all-pairs precomputation step, the running time and subsequent storage costs of which can be prohibitive. In this work we consider an alternative approach where we precompute and store goal bounding data only for grid cells which are also jump points. Since the number of jump points is usually much smaller than the total number of grid cells, we can save up to orders of magnitude in preprocessing time and space. Considerable precomputation savings do not necessarily mean performance degradation. For a second contribution we show how canonical orderings, partial expansion strategies and enhanced intermediate pruning can be leveraged to improve online query performance despite a reduction in preprocessed data. The combination of faster preprocessing and stronger online reasoning leads to three new and highly performant algorithms: JPS+BB+ and Two-Oracle Pathfinding Search (TOPS) based on search, and Topping+ based on path extraction. We give a theoretical analysis showing that each method is complete and optimal. We also report convincing gains in a comprehensive empirical evaluation that includes almost all current and cutting-edge algorithms for grid-based pathfinding.

Reinforcement learning is about learning agent models that make the best sequential decisions in unknown environments. In an unknown environment, the agent needs to explore the environment while exploiting the collected information, which usually forms a sophisticated problem to solve. Derivative-free optimization, meanwhile, is capable of solving sophisticated problems. It commonly uses a sampling-and-updating framework to iteratively improve the solution, where exploration and exploitation are also needed to be well balanced. Therefore, derivative-free optimization deals with a similar core issue as reinforcement learning, and has been introduced in reinforcement learning approaches, under the names of learning classifier systems and neuroevolution/evolutionary reinforcement learning. Although such methods have been developed for decades, recently, derivative-free reinforcement learning exhibits attracting increasing attention. However, recent survey on this topic is still lacking. In this article, we summarize methods of derivative-free reinforcement learning to date, and organize the methods in aspects including parameter updating, model selection, exploration, and parallel/distributed methods. Moreover, we discuss some current limitations and possible future directions, hoping that this article could bring more attentions to this topic and serve as a catalyst for developing novel and efficient approaches.

With astonishing speed, bandwidth, and scale, Mobile Edge Computing (MEC) has played an increasingly important role in the next generation of connectivity and service delivery. Yet, along with the massive deployment of MEC servers, the ensuing energy issue is now on an increasingly urgent agenda. In the current context, the large scale deployment of renewable-energy-supplied MEC servers is perhaps the most promising solution for the incoming energy issue. Nonetheless, as a result of the intermittent nature of their power sources, these special design MEC server must be more cautious about their energy usage, in a bid to maintain their service sustainability as well as service standard. Targeting optimization on a single-server MEC scenario, we in this paper propose NAFA, an adaptive processor frequency adjustment solution, to enable an effective plan of the server's energy usage. By learning from the historical data revealing request arrival and energy harvest pattern, the deep reinforcement learning-based solution is capable of making intelligent schedules on the server's processor frequency, so as to strike a good balance between service sustainability and service quality. The superior performance of NAFA is substantiated by real-data-based experiments, wherein NAFA demonstrates up to 20% increase in average request acceptance ratio and up to 50% reduction in average request processing time.

It is well-known that standard neural networks, even with a high classification accuracy, are vulnerable to small $\ell_\infty$-norm bounded adversarial perturbations. Although many attempts have been made, most previous works either can only provide empirical verification of the defense to a particular attack method, or can only develop a certified guarantee of the model robustness in limited scenarios. In this paper, we seek for a new approach to develop a theoretically principled neural network that inherently resists $\ell_\infty$ perturbations. In particular, we design a novel neuron that uses $\ell_\infty$-distance as its basic operation (which we call $\ell_\infty$-dist neuron), and show that any neural network constructed with $\ell_\infty$-dist neurons (called $\ell_{\infty}$-dist net) is naturally a 1-Lipschitz function with respect to $\ell_\infty$-norm. This directly provides a rigorous guarantee of the certified robustness based on the margin of prediction outputs. We also prove that such networks have enough expressive power to approximate any 1-Lipschitz function with robust generalization guarantee. Our experimental results show that the proposed network is promising. Using $\ell_{\infty}$-dist nets as the basic building blocks, we consistently achieve state-of-the-art performance on commonly used datasets: 93.09% certified accuracy on MNIST ($\epsilon=0.3$), 79.23% on Fashion MNIST ($\epsilon=0.1$) and 35.10% on CIFAR-10 ($\epsilon=8/255$).

Lexical inference (LI) denotes the task of deciding Recently, transfer learning has become ubiquitous whether or not an entailment relation holds between in NLP; Transformer (Vaswani et al., two lexical items. It is therefore related to the detection 2017) language models (LMs) pretrained on large of other lexical relations like hyponymy amounts of textual data (Devlin et al., 2019a; Liu between nouns (Hearst, 1992), e.g., dog animal, et al., 2019) form the basis of a lot of current stateof-the-art or troponymy between verbs (Fellbaum and Miller, models. Besides zero-and few-shot capabilities 1990), e.g., to traipse to walk. Lexical inference (Radford et al., 2019; Brown et al., 2020), in context (LIiC) adds the problem of disambiguating pretrained LMs have also been found to acquire the pair of lexical items in a given context before factual and relational knowledge during pretraining reasoning about the inference question.