This thesis investigates share buybacks, specifically share buyback announcements. It addresses how to recognize such announcements, the excess return of share buybacks, and the prediction of returns after a share buyback announcement. We illustrate two NLP approaches for the automated detection of share buyback announcements. Even with very small amounts of training data, we can achieve an accuracy of up to 90%. This thesis utilizes these NLP methods to generate a large dataset consisting of 57,155 share buyback announcements. By analyzing this dataset, this thesis aims to show that most companies, which have a share buyback announced are underperforming the MSCI World. A minority of companies, however, significantly outperform the MSCI World. This significant overperformance leads to a net gain when looking at the averages of all companies. If the benchmark index is adjusted for the respective size of the companies, the average overperformance disappears, and the majority underperforms even greater. However, it was found that companies that announce a share buyback with a volume of at least 1% of their market cap, deliver, on average, a significant overperformance, even when using an adjusted benchmark. It was also found that companies that announce share buybacks in times of crisis emerge better than the overall market. Additionally, the generated dataset was used to train 72 machine learning models. Through this, it was able to find many strategies that could achieve an accuracy of up to 77% and generate great excess returns. A variety of performance indicators could be improved across six different time frames and a significant overperformance was identified. This was achieved by training several models for different tasks and time frames as well as combining these different models, generating significant improvement by fusing weak learners, in order to create one strong learner.

Outlier detection tasks have been playing a critical role in AI safety. There has been a great challenge to deal with this task. Observations show that deep neural network classifiers usually tend to incorrectly classify out-of-distribution (OOD) inputs into in-distribution classes with high confidence. Existing works attempt to solve the problem by explicitly imposing uncertainty on classifiers when OOD inputs are exposed to the classifier during training. In this paper, we propose an alternative probabilistic paradigm that is both practically useful and theoretically viable for the OOD detection tasks. Particularly, we impose statistical independence between inlier and outlier data during training, in order to ensure that inlier data reveals little information about OOD data to the deep estimator during training. Specifically, we estimate the statistical dependence between inlier and outlier data through the Hilbert-Schmidt Independence Criterion (HSIC), and we penalize such metric during training. We also associate our approach with a novel statistical test during the inference time coupled with our principled motivation. Empirical results show that our method is effective and robust for OOD detection on various benchmarks. In comparison to SOTA models, our approach achieves significant improvement regarding FPR95, AUROC, and AUPR metrics. Code is available: \url{https://github.com/jylins/hood}.

Imitation learning (IL) is a general learning paradigm for tackling sequential decision-making problems. Interactive imitation learning, where learners can interactively query for expert demonstrations, has been shown to achieve provably superior sample efficiency guarantees compared with its offline counterpart or reinforcement learning. In this work, we study classification-based online imitation learning (abbrev. $\textbf{COIL}$) and the fundamental feasibility to design oracle-efficient regret-minimization algorithms in this setting, with a focus on the general nonrealizable case. We make the following contributions: (1) we show that in the $\textbf{COIL}$ problem, any proper online learning algorithm cannot guarantee a sublinear regret in general; (2) we propose $\textbf{Logger}$, an improper online learning algorithmic framework, that reduces $\textbf{COIL}$ to online linear optimization, by utilizing a new definition of mixed policy class; (3) we design two oracle-efficient algorithms within the $\textbf{Logger}$ framework that enjoy different sample and interaction round complexity tradeoffs, and conduct finite-sample analyses to show their improvements over naive behavior cloning; (4) we show that under the standard complexity-theoretic assumptions, efficient dynamic regret minimization is infeasible in the $\textbf{Logger}$ framework. Our work puts classification-based online imitation learning, an important IL setup, into a firmer foundation.

In this paper, we introduce a novel online model-based reinforcement learning algorithm that uses Unscented Transform to propagate uncertainty for the prediction of the future reward. Previous approaches either approximate the state distribution at each step of the prediction horizon with a Gaussian, or perform Monte Carlo simulations to estimate the rewards. Our method, depending on the number of sigma points employed, can propagate either mean and covariance with minimal points, or higher-order moments with more points similarly to Monte Carlo. The whole framework is implemented as a computational graph for online training. Furthermore, in order to prevent explosion in the number of sigma points when propagating through a generic state-dependent uncertainty model, we add sigma-point expansion and contraction layers to our graph, which are designed using the principle of moment matching. Finally, we propose gradient descent inspired by Sequential Quadratic Programming to update policy parameters in the presence of state constraints. We demonstrate the proposed method with two applications in simulation. The first one designs a stabilizing controller for the cart-pole problem when the dynamics is known with state-dependent uncertainty. The second example, following up on our previous work, tunes the parameters of a control barrier function-based Quadratic Programming controller for a leader-follower problem in the presence of input constraints.

Pandemics, in addition to affecting the health of populations, can have huge impacts on their social and economic behavior. These factors, on the other hand, have the potential to feed back to and influence the disease spreading. It is important to systematically study these interrelations, to determine which ones have significant effects, and whether the effects are adverse or beneficial. Our recently developed epidemic model with agent-based and geographical elements is used in this study for such a purpose. We perform an extensive parameter space exploration of the socio-economic part of the model, including factors like the attitudes (called values) of the agents towards the disease spreading, health, economic situation, and regulations by government agents. We search for prominent patterns from the resulting simulated data using basic classification tools, namely self-organizing maps and principal component analysis. We seek to isolate the most important value parameters of the population and government agents influencing the disease spreading speed and patterns, and monitor different quantities of the model output, such as infection rates, the propagation speed of the epidemic, economic activity, government regulations, and the compliance of population. Out of these, the ones describing the epidemic spreading were resulting in the most distinctive clustering of the data, and they were selected as the basis of the remaining analysis. We relate the found clusters to three distinct types of disease spreading: wave-like, chaotic, and transitional spreading patterns. The most important value parameter contributing to phase changes between these phases was found to be the compliance of the population agents towards the government regulations.

Even human intelligence system fails to offer 100% accuracy in identifying speeches from a specific individual. Machine intelligence is trying to mimic humans in speaker identification problems through various approaches to speech feature extraction and speech modeling techniques. This paper presents a text-independent speaker identification system that employs Mel Frequency Cepstral Coefficients (MFCC) for feature extraction and k-Nearest Neighbor (kNN) for classification. The maximum cross-validation accuracy obtained was 60%. This will be improved upon in subsequent research.

Classical machine learning (ML) provides a potentially powerful approach to solving challenging quantum many-body problems in physics and chemistry. However, the advantages of ML over more traditional methods have not been firmly established. In this work, we prove that classical ML algorithms can efficiently predict ground state properties of gapped Hamiltonians in finite spatial dimensions, after learning from data obtained by measuring other Hamiltonians in the same quantum phase of matter. In contrast, under widely accepted complexity theory assumptions, classical algorithms that do not learn from data cannot achieve the same guarantee. We also prove that classical ML algorithms can efficiently classify a wide range of quantum phases of matter. Our arguments are based on the concept of a classical shadow, a succinct classical description of a many-body quantum state that can be constructed in feasible quantum experiments and be used to predict many properties of the state. Extensive numerical experiments corroborate our theoretical results in a variety of scenarios, including Rydberg atom systems, 2D random Heisenberg models, symmetry-protected topological phases, and topologically ordered phases.

Investment professionals rely on extrapolating company revenue into the future (i.e. revenue forecast) to approximate the valuation of scaleups (private companies in a high-growth stage) and inform their investment decision. This task is manual and empirical, leaving the forecast quality heavily dependent on the investment professionals' experiences and insights. Furthermore, financial data on scaleups is typically proprietary, costly and scarce, ruling out the wide adoption of data-driven approaches. To this end, we propose a simulation-informed revenue extrapolation (SiRE) algorithm that generates fine-grained long-term revenue predictions on small datasets and short time-series. SiRE models the revenue dynamics as a linear dynamical system (LDS), which is solved using the EM algorithm. The main innovation lies in how the noisy revenue measurements are obtained during training and inferencing. SiRE works for scaleups that operate in various sectors and provides confidence estimates. The quantitative experiments on two practical tasks show that SiRE significantly surpasses the baseline methods by a large margin. We also observe high performance when SiRE extrapolates long-term predictions from short time-series. The performance-efficiency balance and result explainability of SiRE are also validated empirically. Evaluated from the perspective of investment professionals, SiRE can precisely locate the scaleups that have a great potential return in 2 to 5 years. Furthermore, our qualitative inspection illustrates some advantageous attributes of the SiRE revenue forecasts.

Hashing that projects data into binary codes has shown extraordinary talents in cross-modal retrieval due to its low storage usage and high query speed. Despite their empirical success on some scenarios, existing cross-modal hashing methods usually fail to cross modality gap when fully-paired data with plenty of labeled information is nonexistent. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose Deep Manifold Hashing (DMH), a novel method of dividing the problem of semi-paired unsupervised cross-modal retrieval into three sub-problems and building one simple yet efficiency model for each sub-problem. Specifically, the first model is constructed for obtaining modality-invariant features by complementing semi-paired data based on manifold learning, whereas the second model and the third model aim to learn hash codes and hash functions respectively. Extensive experiments on three benchmarks demonstrate the superiority of our DMH compared with the state-of-the-art fully-paired and semi-paired unsupervised cross-modal hashing methods.

Accurate traffic forecasting is essential for smart cities to achieve traffic control, route planning, and flow detection. Although many spatial-temporal methods are currently proposed, these methods are deficient in capturing the spatial-temporal dependence of traffic data synchronously. In addition, most of the methods ignore the dynamically changing correlations between road network nodes that arise as traffic data changes. We propose a neural network-based Spatial-Temporal Interactive Dynamic Graph Convolutional Network (STIDGCN) to address the above challenges for traffic forecasting. Specifically, we propose an interactive dynamic graph convolution structure, which divides the sequences at intervals and synchronously captures the traffic data's spatial-temporal dependence through an interactive learning strategy. The interactive learning strategy makes STIDGCN effective for long-term prediction. We also propose a novel dynamic graph convolution module to capture the dynamically changing correlations in the traffic network, consisting of a graph generator and fusion graph convolution. The dynamic graph convolution module can use the input traffic data and pre-defined graph structure to generate a graph structure. It is then fused with the defined adaptive adjacency matrix to generate a dynamic adjacency matrix, which fills the pre-defined graph structure and simulates the generation of dynamic associations between nodes in the road network. Extensive experiments on four real-world traffic flow datasets demonstrate that STIDGCN outperforms the state-of-the-art baseline.