Диссертации, представленные на защиту и подготовленные в НИУ ВШЭ

Monetary instability is a persistent concern for emerging market economies, especially due to their vulnerability to external financial shocks. These shocks often reveal structural weaknesses in how these economies are positioned within the global financial system. This dissertation examines two important sources of such instability: changes in U.S. interest rates and uncertainty in U.S. economic policy. It first investigates the effects of these external factors on macroeconomic outcomes in emerging markets. The analysis then turns to the domestic level, using India as a case study to examine how money demand can be forecast more accurately. A panel structural VAR is used to study the effects of U.S. interest rate shocks, while a GMM-based panel VAR examines the impact of U.S. economic policy uncertainty. The results indicate that both higher interest rates and greater policy uncertainty in the U.S. are associated with exchange rate depreciation, rising inflation, and tighter financial conditions in emerging markets. In the case of India, the dissertation compares several machine learning models for forecasting money demand and finds that methods like LSTM and LASSO perform particularly well. These findings highlight distinct sources of monetary instability and offer practical insights that may be useful for both researchers and policymakers.

Nowadays, ontologies are widely used to improve the convenience of information organisation and access to it in fields such as artificial intelligence, software engineering, biomedical informatics, healthcare, enterprise bookmarking, industrial projects, etc. We focus on Ontology-Based Data Access (OBDA) with expressive ontologies, where an ontology is used as a helpful tool for supporting query answering for distributed and heterogeneous data sources. Answering various types of queries mediated by a description logic ontology has been known as an essential reasoning problem in knowledge representation since the early 1990s. We explore the practical potential of specific expressive ontology with a covering axiom in ontology-mediated query (OMQ) answering tasks and focus on challenges associated with chosen ontology type. This study allows us to provide theoretical boundaries of covering axiom usage for OBDA and constructive rewriting of OMQs answering into datalog programs. Additionally, we compare two different approaches to identify the profitability of logic reasoning via OMQ rewriting and graph neural network data labelling followed by querying obtained full-labelled graph.

In this PhD dissertation, we address the problems of optimal stopping and learning in Markov decision processes used in reinforcement learning (RL). In the first direction, we derive complexity estimates for the algorithm called Weighted Stochastic Mesh (WSM) and give a new method for comparing the complexity of optimal stopping algorithms with the semi tractability index. We show that WSM is optimal with respect to this criterion when the commonly used regression methods are much less effective. For reinforcement learning, we give a non-asymptotic convergence analysis of a stochastic approximation scheme with two time scales - gradient TD - under assumptions of "martingale increment" noise - buffer replay - and of "Markov noise" (when learning is done along a single run). We obtain upper bounds that are rate-optimal by constructing an error expansion method that provides accurate control of the remainders terms. We also present a new algorithm for variance reduction in policy gradient schemes. The proposed approach is based on minimising an estimator for the empirical variance of the weighted rewards. We establish theoretical and practical gains over the classical actor-critic (A2C) method.