Adaptivity is an important yet under-studied property in modern optimization theory. The gap between the state-of-the-art theory and the current practice is striking in that algorithms with desirable theoretical guarantees typically involve drastically different settings of hyperparameters, such as step-size schemes and batch sizes, in different regimes. Despite the appealing theoretical results, such divisive strategies provide little, if any, insight to practitioners to select algorithms that work broadly without tweaking the hyperparameters. In this work, blending the "geometrization" technique introduced by Lei & Jordan 2016 and the \texttt{SARAH} algorithm of Nguyen et al., 2017, we propose the Geometrized \texttt{SARAH} algorithm for non-convex finite-sum and stochastic optimization. Our algorithm is proved to achieve adaptivity to both the magnitude of the target accuracy and the Polyak-\L{}ojasiewicz (PL) constant if present. In addition, it achieves the best-available convergence rate for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives.

XCS constitutes the most deeply investigated classifier system today. It bears strong potentials and comes with inherent capabilities for mastering a variety of different learning tasks. Besides outstanding successes in various classification and regression tasks, XCS also proved very effective in certain multi-step environments from the domain of reinforcement learning. Especially in the latter domain, recent advances have been mainly driven by algorithms which model their policies based on deep neural networks -- among which the Deep-Q-Network (DQN) is a prominent representative. Experience Replay (ER) constitutes one of the crucial factors for the DQN's successes, since it facilitates stabilized training of the neural network-based Q-function approximators. Surprisingly, XCS barely takes advantage of similar mechanisms that leverage stored raw experiences encountered so far. To bridge this gap, this paper investigates the benefits of extending XCS with ER. On the one hand, we demonstrate that for single-step tasks ER bears massive potential for improvements in terms of sample efficiency. On the shady side, however, we reveal that the use of ER might further aggravate well-studied issues not yet solved for XCS when applied to sequential decision problems demanding for long-action-chains.

Deep Learning (DL) techniques for Natural Language Processing have been evolving remarkably fast. Recently, the DL advances in language modeling, machine translation and paragraph understanding are so prominent that the potential of DL in Software Engineering cannot be overlooked, especially in the field of program learning. To facilitate further research and applications of DL in this field, we provide a comprehensive review to categorize and investigate existing DL methods for source code modeling and generation. To address the limitations of the traditional source code models, we formulate common program learning tasks under an encoder-decoder framework. After that, we introduce recent DL mechanisms suitable to solve such problems. Then, we present the state-of-the-art practices and discuss their challenges with some recommendations for practitioners and researchers as well.

The Gaussian process (GP) model, which has been extensively applied as priors of functions, has demonstrated excellent performance. The specification of a large number of parameters affects the computational efficiency and the feasibility of implementation of a control strategy. We propose a linear model to approximate GPs; this model expands the GP model by a series of basis functions. Several examples and simulation studies are presented to demonstrate the advantages of the proposed method. A control strategy is provided with the proposed linear model. Keywords: Data mining, forecasting, stochastic processes, control strategies INTRODUCTION The Gaussian process (GP) is a powerful modeling tool that has many applications in research and practice. It provides a practical and probabilistic approach to learning in kernel machines. The GP is extensively applied as a prior of a true function.

Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision trees are smaller and more explainable. We present dtControl, an easily extensible tool for representing memoryless controllers as decision trees. We give a comprehensive evaluation of various decision tree learning algorithms applied to 10 case studies arising out of correct-by-construction controller synthesis. These algorithms include two new techniques, one for using arbitrary linear binary classifiers in the decision tree learning, and one novel approach for determinizing controllers during the decision tree construction. In particular the latter turns out to be extremely efficient, yielding decision trees with a single-digit number of decision nodes on 5 of the case studies.

An influential recent line of work [KLS09, ABL13, DKK 16, LRV16, CSV17, KS17a, KS17b, HL17, DKK 18, DKS17a, KKM18] has focused on designing algorithms for basic statistical estimation tasks in the presence of adversarial outliers. This has led to a body of work on outlier-robust estimation of basic parameters of distributions such as mean, covariance [DKK 16, DKS17b, CDG19, DKK 17, DKK 18, CDGW19] and moment tensors [KS17b] along with applications to "downstream" learning tasks such as linear and polynomial regression [DKS17c, KKM18, DKK 19, PSBR18]. The upshot of this line of work is a detailed understanding of efficient robust estimation when the fraction of inliers ( 1/2), but a fixed fraction of arbitrary adversarial outliers in the input data. In this work, we focus on the harsher list-decodable estimation model where the fraction of inliersαis 1/2 - i.e.,a majority of the input sample are outliers. First considered in [BBV08] in the context of clustering, this was proposed as a model for untrusted data in a recent influential recent work of Charikar, Steinhardt and Valiant [CSV17]. Since unique recovery is informationtheoretically impossible in this setting, the goal is to recover a small (ideally O(1/α)) size list of parameters one of which is guaranteed to be close to those of the inlier distribution. A recent series of works have resulted in a high-level blueprint based on the sum-of-squares method for listdecodable estimation yielding algorithms for list-decodable mean estimation [DKS18, KS17a] and linear regression [KKK19, RY20]. We extend this line of work by giving the first efficient algorithm for list-decodable subspace recovery. In this setting, we are given data with α fraction inliers generated i.i.d.

Creating maps is an essential task in robotics and provides the basis for effective planning and navigation. In this paper, we learn a compact and continuous implicit surface map of an environment from a stream of range data with known poses. For this, we create and incrementally adjust an ensemble of approximate Gaussian process (GP) experts which are each responsible for a different part of the map. Instead of inserting all arriving data into the GP models, we greedily trade-off between model complexity and prediction error. Our algorithm therefore uses less resources on areas with few geometric features and more where the environment is rich in variety. We evaluate our approach on synthetic and real-world data sets and analyze sensitivity to parameters and measurement noise. The results show that we can learn compact and accurate implicit surface models under different conditions, with a performance comparable to or better than that of exact GP regression with subsampled data.

Privacy policies are legal documents that describe how a website will collect, use, and distribute a user's data. Unfortunately, such documents are often overly complicated and filled with legal jargon; making it difficult for users to fully grasp what exactly is being collected and why. Our solution to this problem is to provide users with a coverage analysis of a given website's privacy policy using a wide range of classical machine learning and deep learning techniques. Given a website's privacy policy, the classifier identifies the associated data practice for each logical segment. These data practices/labels are taken directly from the OPP-115 corpus. For example, the data practice "Data Retention" refers to how long a website stores a user's information. The coverage analysis allows users to determine how many of the ten possible data practices are covered, along with identifying the sections that correspond to the data practices of particular interest.

Insect monitoring is crucial for understanding the consequences of rapid ecological changes, but taxa identification currently requires tedious manual expert work and cannot be scaled-up efficiently. Deep convolutional neural networks (CNNs), provide a viable way to significantly increase the biomonitoring volumes. However, taxa abundances are typically very imbalanced and the amounts of training images for the rarest classes are simply too low for deep CNNs. As a result, the samples from the rare classes are often completely missed, while detecting them has biological importance. In this paper, we propose combining the trained deep CNN with one-class classifiers to improve the rare species identification. One-class classification models are traditionally trained with much fewer samples and they can provide a mechanism to indicate samples potentially belonging to the rare classes for human inspection. Our experiments confirm that the proposed approach may indeed support moving towards partial automation of the taxa identification task.