Learning from data streams is emerging as an important application area. When the environment changes, it is necessary to rely on on-line learning with the capability to adapt to changing conditions a.k.a. concept drifts. Adapting to concept drifts entails forgetting some or all of the old acquired knowledge when the concept changes while accumulating knowledge regarding the supposedly stationary underlying concept. This tradeoff is called the stability-plasticity dilemma. Ensemble methods have been among the most successful approaches. However, the management of the ensemble which ultimately controls how past data is forgotten has not been thoroughly investigated so far. Our work shows the importance of the forgetting strategy by comparing several approaches. The results thus obtained lead us to propose a new ensemble method with an enhanced forgetting strategy to adapt to concept drifts. Experimental comparisons show that our method compares favorably with the well-known state-of-the-art systems. The majority of previous works focused only on means to detect changes and to adapt to them. In our work, we go one step further by introducing a meta-learning mechanism that is able to detect relevant states of the environment, to recognize recurring contexts and to anticipate likely concepts changes. Hence, the method we suggest, deals with both the challenge of optimizing the stability-plasticity dilemma and with the anticipation and recognition of incoming concepts. This is accomplished through an ensemble method that controls a ensemble of incremental learners. The management of the ensemble of learners enables one to naturally adapt to the dynamics of the concept changes with very few parameters to set, while a learning mechanism managing the changes in the ensemble provides means for the anticipation of, and the quick adaptation to, the underlying modification of the context.

A problem that exhibition halls have is the balance between having good indoor air quality andminimizing energy waste due to the naturally slow decrease of CO2 concentration, which causes Heat-ing, Ventilation and Air-Conditioning systems to keep ventilating empty halls when occupants have leftthe vicinity. Several studies have been made on the topic of CO2 prediction and occupancy predictionbased on CO2 for smaller spaces such as offices and schools. However, few studies have been madefor bigger venues where a larger group of people gather. An online machine learning model using theRiver library was developed to tackle this problem by predicting the CO2 ahead of time. Five datasetswere used for training and predicting, three with real data and two with simulated data. The resultsfrom this model was compared with three already developed traditional models in order to evaluate theperformance of an online machine learning model compared to traditional models. The online machinelearning model was successful in predicting CO2 one hour ahead of time considerably faster than thetraditional models, achieving a r2 score of up to 0.95.

De nombreuses applications de flux de données ont vu le jour au cours des dernières années. Lorsque l'environnement évolue, il est nécessaire de s'appuyer sur un apprentissage en ligne pouvant s'adapter aux conditions changeantes, alias dérives de concept. L'adaptation aux dérives de concept implique d'oublier une partie ou la totalité des connaissances acquises lorsque le concept change, tout en accumulant des connaissances sur le concept sous-jacent supposé stationnaire. Ce compromis est appelé le dilemme stabilité-plasticité.Les méthodes d'ensemble ont été parmi les approches les plus réussies. Cependant, la gestion de l'ensemble qui détermine les informations à oublier n'a pas été complètement étudiée jusqu'ici. Notre travail montre l'importance de la stratégie de l'oubli en comparant plusieurs approches. Les résultats ainsi obtenus nous amènent à proposer une nouvelle méthode d'ensemble avec une stratégie d'oubli conçue pour s'adapter aux dérives de concept. Des évaluations empiriques montrent que notre méthode se compare favorablement aux systèmes adaptatifs de l'état de l'art.Les majorité des anciens travaux réalisés se sont focalisés sur la détection des changements de concept, ainsi que les méthodes permettant d'adapter le système d'apprentissage aux changements. Dans ce travail, nous allons plus loin en introduisant un mécanisme d'anticipation capable de détecter des états pertinents de l'environnement, de reconnaître les contextes récurrents et d'anticiper les changements de concept susceptibles.Par conséquent, la méthode que nous proposons traite à la fois le défi d'optimiser le dilemme stabilité-plasticité, l'anticipation et la reconnaissance des futurs concepts. Ceci est accompli grâce à une méthode d'ensemble qui contrôle un comité d'apprenants. D'une part, la gestion de l'ensemble permet de s'adapter naturellement à la dynamique des changements de concept avec peu de paramètres à régler. D'autre part, un mécanisme d'apprentissage surveillant les changements dans l'ensemble fournit des moyens pour anticiper la modification sous-jacente du contexte. / Learning from data streams is emerging as an important application area. When the environment changes, it is necessary to rely on on-line learning with the capability to adapt to changing conditions a.k.a. concept drifts. Adapting to concept drifts entails forgetting some or all of the old acquired knowledge when the concept changes while accumulating knowledge regarding the supposedly stationary underlying concept. This tradeoff is called the stability-plasticity dilemma. Ensemble methods have been among the most successful approaches. However, the management of the ensemble which ultimately controls how past data is forgotten has not been thoroughly investigated so far. Our work shows the importance of the forgetting strategy by comparing several approaches. The results thus obtained lead us to propose a new ensemble method with an enhanced forgetting strategy to adapt to concept drifts. Experimental comparisons show that our method compares favorably with the well-known state-of-the-art systems. The majority of previous works focused only on means to detect changes and to adapt to them. In our work, we go one step further by introducing a meta-learning mechanism that is able to detect relevant states of the environment, to recognize recurring contexts and to anticipate likely concepts changes. Hence, the method we suggest, deals with both the challenge of optimizing the stability-plasticity dilemma and with the anticipation and recognition of incoming concepts. This is accomplished through an ensemble method that controls a ensemble of incremental learners. The management of the ensemble of learners enables one to naturally adapt to the dynamics of the concept changes with very few parameters to set, while a learning mechanism managing the changes in the ensemble provides means for the anticipation of, and the quick adaptation to, the underlying modification of the context.

Online supervised learning from fast-evolving imbalanced data streams has applications in many areas. That is, the development of techniques that are able to handle highly skewed class distributions (or 'class imbalance') is an important area of research in domains such as manufacturing, the environment, and health. Solutions should be able to analyze large repositories in near real-time and provide accurate models to describe rare classes that may appear infrequently or in bursts while continuously accommodating new instances. Although numerous online learning methods have been proposed to handle binary class imbalance, solutions suitable for multi-class streams with varying degrees of imbalance in evolving streams have received limited attention. To address this knowledge gap, the first contribution of this thesis introduces the Online Learning from Imbalanced Multi-Class Streams through Dynamic Sampling (DynaQ) algorithm for learning in such multi-class imbalanced settings. Our approach utilizes a queue-based learning method that dynamically creates an instance queue for each class. The number of instances is balanced by maintaining a queue threshold and removing older samples during training. In addition, new and rare classes are dynamically added to the training process as they appear. Our experimental results confirm a noticeable improvement in minority-class detection and classification performance. A comparative evaluation shows that the DynaQ algorithm outperforms the state-of-the-art approaches. Our second contribution in this thesis focuses on fairness-aware learning from imbalanced streams. Our work is motivated by the observation that the decisions made by online learning algorithms may negatively impact individuals or communities. Indeed, the development of approaches to handle these concerns is an active area of research in the machine learning community. However, most existing methods process the data in offline settings and are not directly suitable for online learning from evolving data streams. Further, these techniques fail to take the effects of class imbalance, on fairness-aware supervised learning into account. In addition, recent fairness-aware online learning supervised learning approaches focus on one sensitive attribute only, which may lead to subgroup discrimination. In a fair classification, the equality of fairness metrics across multiple overlapping groups must be considered simultaneously. In our second contribution, we thus address the combined problem of fairness-aware online learning from imbalanced evolving streams, while considering multiple sensitive attributes. To this end, we introduce the Multi-Sensitive Queue-based Online Fair Learning (MQ-OFL) algorithm, an online fairness-aware approach, which maintains valid and fair models over evolving streams. MQ-OFL changes the training distribution in an online fashion based on both stream imbalance and discriminatory behavior of the model evaluated over the historical stream. We compare our MQ-OFL method with state-of-art studies on real-world datasets and present comparative insights on the performance. Our final contribution focuses on explainability and interpretability in fairness-aware online learning. This research is guided by the concerns raised due to the black-box nature of models, concealing internal logic from users. This lack of transparency poses practical and ethical challenges, particularly when these algorithms make decisions in finance, healthcare, and marketing domains. These systems may introduce biases and prejudices during the learning phase by utilizing complex machine learning algorithms and sensitive data. Consequently, decision models trained on such data may make unfair decisions and it is important to realize such issues before deploying the models. To address this issue, we introduce techniques for interpreting the outcomes of fairness-aware online learning. Through a case study predicting income based on features such as ethnicity, biological sex, age, and education level, we demonstrate how our fairness-aware learning process (MQ-OFL) maintains a balance between accuracy and discrimination trade-off using global and local surrogate models.

<p>Sequential decision-making is a fundamental class of problem that motivates algorithm designs of online machine learning and reinforcement learning. Arguably, the resulting online algorithms have supported modern online service industries for their data-driven real-time automated decision making. The applications span across different industries, including dynamic pricing (Marketing), recommendation (Advertising), and dosage finding (Clinical Trial). In this dissertation, we contribute fundamental statistical design advances for sequential decision-making algorithms, leaping progress in theory and application of online learning and sequential decision making under uncertainty including online sparse learning, finite-armed bandits, and high-dimensional online decision making. Our work locates at the intersection of decision-making algorithm designs, online statistical machine learning, and operations research, contributing new algorithms, theory, and insights to diverse fields including optimization, statistics, and machine learning.</p> <p><br></p> <p>In part I, we contribute a theoretical framework of continuous risk monitoring for regularized online statistical learning. Such theoretical framework is desirable for modern online service industries on monitoring deployed model's performance of online machine learning task. In the first project (Chapter 1), we develop continuous risk monitoring for the online Lasso procedure and provide an always-valid algorithm for high-dimensional dynamic pricing problems. In the second project (Chapter 2), we develop continuous risk monitoring for online matrix regression and provide new algorithms for rank-constrained online matrix completion problems. Such theoretical advances are due to our elegant interplay between non-asymptotic martingale concentration theory and regularized online statistical machine learning.</p> <p><br></p> <p>In part II, we contribute a bootstrap-based methodology for finite-armed bandit problems, termed Residual Bootstrap exploration. Such a method opens a possibility to design model-agnostic bandit algorithms without problem-adaptive optimism-engineering and instance-specific prior-tuning. In the first project (Chapter 3), we develop residual bootstrap exploration for multi-armed bandit algorithms and shows its easy generalizability to bandit problems with complex or ambiguous reward structure. In the second project (Chapter 4), we develop a theoretical framework for residual bootstrap exploration in linear bandit with fixed action set. Such methodology advances are due to our development of non-asymptotic theory for the bootstrap procedure.</p> <p><br></p> <p>In part III, we contribute application-driven insights on the exploration-exploitation dilemma for high-dimensional online decision-making problems. Such insights help practitioners to implement effective high-dimensional statistics methods to solve online decisionmaking problems. In the first project (Chapter 5), we develop a bandit sampling scheme for online batch high-dimensional decision making, a practical scenario in interactive marketing, and sequential clinical trials. In the second project (Chapter 6), we develop a bandit sampling scheme for federated online high-dimensional decision-making to maintain data decentralization and perform collaborated decisions. These new insights are due to our new bandit sampling design to address application-driven exploration-exploitation trade-offs effectively. </p>