In this paper, we study user association and wireless bandwidth allocation for a hierarchical federated learning system that consists of mobile users, edge servers, and a cloud server. To minimize the length of a global round in hierarchical federated learning with equal bandwidth allocation, we formulate a combinatorial optimization problem. We design the twin sorting dynamic programming (TSDP) algorithm that obtains a globally optimal solution in polynomial time when there are two edge servers. In addition, we put forward the TSDP-assisted algorithm for user association when there are three or more edge servers. Furthermore, given a user association matrix, we formulate and solve a convex optimization problem for optimal wireless bandwidth allocation. Simulation results show that the proposed approach outperforms a number of alternative schemes.

Robust partially observable Markov decision processes (robust POMDPs) extend classical POMDPs to handle additional uncertainty on the transition and observation probabilities via so-called uncertainty sets. Policies for robust POMDPs must not only be memory-based to account for partial observability but also robust against model uncertainty to account for the worst-case instances from the uncertainty sets. We propose the pessimistic iterative planning (PIP) framework, which finds robust memory-based policies for robust POMDPs. PIP alternates between two main steps: (1) selecting an adversarial (non-robust) POMDP via worst-case probability instances from the uncertainty sets; and (2) computing a finite-state controller (FSC) for this adversarial POMDP. We evaluate the performance of this FSC on the original robust POMDP and use this evaluation in step (1) to select the next adversarial POMDP. Within PIP, we propose the rFSCNet algorithm. In each iteration, rFSCNet finds an FSC through a recurrent neural network trained using supervision policies optimized for the adversarial POMDP. The empirical evaluation in four benchmark environments showcases improved robustness against a baseline method in an ablation study and competitive performance compared to a state-of-the-art robust POMDP solver.

PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with respect to a chosen loss function. In classification tasks, due to the non-convex nature of the 0-1 loss, a convex surrogate loss is often used, and thus current PAC-Bayesian bounds are primarily specified for this convex surrogate. This work shifts its focus to providing misclassification excess risk bounds for PAC-Bayesian classification when using a convex surrogate loss. Our key ingredient here is to leverage PAC-Bayesian relative bounds in expectation rather than relying on PAC-Bayesian bounds in probability. We demonstrate our approach in several important applications.

By using an parametric value function to replace the Monte-Carlo rollouts for value estimation, the actor-critic (AC) algorithms can reduce the variance of stochastic policy gradient so that to improve the convergence rate. While existing works mainly focus on analyzing convergence rate of AC algorithms under Markovian noise, the impacts of momentum on AC algorithms remain largely unexplored. In this work, we first propose a heavy-ball momentum based advantage actor-critic (\mbox{HB-A2C}) algorithm by integrating the heavy-ball momentum into the critic recursion that is parameterized by a linear function. When the sample trajectory follows a Markov decision process, we quantitatively certify the acceleration capability of the proposed HB-A2C algorithm. Our theoretical results demonstrate that the proposed HB-A2C finds an $\epsilon$-approximate stationary point with $\oo{\epsilon^{-2}}$ iterations for reinforcement learning tasks with Markovian noise. Moreover, we also reveal the dependence of learning rates on the length of the sample trajectory. By carefully selecting the momentum factor of the critic recursion, the proposed HB-A2C can balance the errors introduced by the initialization and the stoschastic approximation.

Moving Target Defense (MTD) has emerged as a proactive and dynamic framework to counteract evolving cyber threats. Traditional MTD approaches often rely on assumptions about the attackers knowledge and behavior. However, real-world scenarios are inherently more complex, with adaptive attackers and limited prior knowledge of their payoffs and intentions. This paper introduces a novel approach to MTD using a Markov Decision Process (MDP) model that does not rely on predefined attacker payoffs. Our framework integrates the attackers real-time responses into the defenders MDP using a dynamic Bayesian Network. By employing a factored MDP model, we provide a comprehensive and realistic system representation. We also incorporate incremental updates to an attack response predictor as new data emerges. This ensures an adaptive and robust defense mechanism. Additionally, we consider the costs of switching configurations in MTD, integrating them into the reward structure to balance execution and defense costs. We first highlight the challenges of the problem through a theoretical negative result on regret. However, empirical evaluations demonstrate the frameworks effectiveness in scenarios marked by high uncertainty and dynamically changing attack landscapes.

Social evolutionary theory seeks to explain increases in the scale and complexity of human societies, from origins to present. Over the course of the twentieth century, social evolutionary theory largely fell out of favor as a way of investigating human history, just as advances in complex systems science and computer science saw the emergence of powerful new conceptions of complex systems, and in particular new methods of measuring complexity. We propose that these advances in our understanding of complex systems and computer science should be brought to bear on our investigations into human history. To that end, we present a new framework for modeling how human societies co-evolve with their biotic environments, recognizing that both a society and its environment are computers. This leads us to model the dynamics of each of those two systems using the same, new kind of computational machine, which we define here. For simplicity, we construe a society as a set of interacting occupations and technologies. Similarly, under such a model, a biotic environment is a set of interacting distinct ecological and climatic processes. This provides novel ways to characterize social complexity, which we hope will cast new light on the archaeological and historical records. Our framework also provides a natural way to formalize both the energetic (thermodynamic) costs required by a society as it runs, and the ways it can extract thermodynamic resources from the environment in order to pay for those costs -- and perhaps to grow with any left-over resources.

A text stream is an ordered sequence of text documents generated over time. A massive amount of such text data is generated by online social platforms every day. Designing an algorithm for such text streams to extract useful information is a challenging task due to unique properties of the stream such as infinite length, data sparsity, and evolution. Thereby, learning useful information from such streaming data under the constraint of limited time and memory has gained increasing attention. During the past decade, although many text stream mining algorithms have proposed, there still exists some potential issues. First, high-dimensional text data heavily degrades the learning performance until the model either works on subspace or reduces the global feature space. The second issue is to extract semantic text representation of documents and capture evolving topics over time. Moreover, the problem of label scarcity exists, whereas existing approaches work on the full availability of labeled data. To deal with these issues, in this thesis, new learning models are proposed for clustering and multi-label learning on text streams.

Deep learning has shown tremendous progress in a wide range of digital pathology and medical image classification tasks. Its integration into safe clinical decision-making support requires robust and reliable models. However, real-world data comes with diversities that often lie outside the intended source distribution. Moreover, when test samples are dramatically different, clinical decision-making is greatly affected. Quantifying predictive uncertainty in models is crucial for well-calibrated predictions and determining when (or not) to trust a model. Unfortunately, many works have overlooked the importance of predictive uncertainty estimation. This paper evaluates whether predictive uncertainty estimation adds robustness to deep learning-based diagnostic decision-making systems. We investigate the effect of various carcinoma distribution shift scenarios on predictive performance and calibration. We first systematically investigate three popular methods for improving predictive uncertainty: Monte Carlo dropout, deep ensemble, and few-shot learning on lung adenocarcinoma classification as a primary disease in whole slide images. Secondly, we compare the effectiveness of the methods in terms of performance and calibration under clinically relevant distribution shifts such as in-distribution shifts comprising primary disease sub-types and other characterization analysis data; out-of-distribution shifts comprising well-differentiated cases, different organ origin, and imaging modality shifts. While studies on uncertainty estimation exist, to our best knowledge, no rigorous large-scale benchmark compares predictive uncertainty estimation including these dataset shifts for lung carcinoma classification.

Generating peptides with desired properties is crucial for drug discovery and biotechnology. Traditional sequence-based and structure-based methods often require extensive datasets, which limits their effectiveness. In this study, we proposed a novel method that utilized autoencoder shaped models to explore the protein embedding space, and generate novel peptide analogs by leveraging protein language models. The proposed method requires only a single sequence of interest, avoiding the need for large datasets. Our results show significant improvements over baseline models in similarity indicators of peptide structures, descriptors and bioactivities. The proposed method validated through Molecular Dynamics simulations on TIGIT inhibitors, demonstrates that our method produces peptide analogs with similar yet distinct properties, highlighting its potential to enhance peptide screening processes.

Reinforcement learning (RL) techniques have been increasingly investigated for dynamic HVAC control in buildings. However, most studies focus on exploring solutions in online or off-policy scenarios without discussing in detail the implementation feasibility or effectiveness of dealing with purely offline datasets or trajectories. The lack of these works limits the real-world deployment of RL-based HVAC controllers, especially considering the abundance of historical data. To this end, this paper comprehensively evaluates the strengths and limitations of state-of-the-art offline RL algorithms by conducting analytical and numerical studies. The analysis is conducted from two perspectives: algorithms and dataset characteristics. As a prerequisite, the necessity of applying offline RL algorithms is first confirmed in two building environments. The ability of observation history modeling to reduce violations and enhance performance is subsequently studied. Next, the performance of RL-based controllers under datasets with different qualitative and quantitative conditions is investigated, including constraint satisfaction and power consumption. Finally, the sensitivity of certain hyperparameters is also evaluated. The results indicate that datasets of a certain suboptimality level and relatively small scale can be utilized to effectively train a well-performed RL-based HVAC controller. Specifically, such controllers can reduce at most 28.5% violation ratios of indoor temperatures and achieve at most 12.1% power savings compared to the baseline controller. In summary, this paper presents our well-structured investigations and new findings when applying offline reinforcement learning to building HVAC systems.