Online multi-task learning (OMTL) enhances streaming data processing by leveraging the inherent relations among multiple tasks. It can be described as an optimization problem in which a single loss function is defined for multiple tasks. Existing gradient-descent-based methods for this problem might suffer from gradient vanishing and poor conditioning issues. Furthermore, the centralized setting hinders their application to online parallel optimization, which is vital to big data analytics. Therefore, this study proposes a novel OMTL framework based on the alternating direction multiplier method (ADMM), a recent breakthrough in optimization suitable for the distributed computing environment because of its decomposable and easy-to-implement nature. The relations among multiple tasks are modeled dynamically to fit the constant changes in an online scenario. In a classical distributed computing architecture with a central server, the proposed OMTL algorithm with the ADMM optimizer outperforms SGD-based approaches in terms of accuracy and efficiency. Because the central server might become a bottleneck when the data scale grows, we further tailor the algorithm to a decentralized setting, so that each node can work by only exchanging information with local neighbors. Experimental results on a synthetic and several real-world datasets demonstrate the efficiency of our methods.

This paper presents the detection of DDoS attacks in IoT networks using machine learning models. Their rapid growth has made them highly susceptible to various forms of cyberattacks, many of whose security procedures are implemented in an irregular manner. It evaluates the efficacy of different machine learning models, such as XGBoost, K-Nearest Neighbours, Stochastic Gradient Descent, and Na\"ive Bayes, in detecting DDoS attacks from normal network traffic. Each model has been explained on several performance metrics, such as accuracy, precision, recall, and F1-score to understand the suitability of each model in real-time detection and response against DDoS threats. This comparative analysis will, therefore, enumerate the unique strengths and weaknesses of each model with respect to the IoT environments that are dynamic and hence moving in nature. The effectiveness of these models is analyzed, showing how machine learning can greatly enhance IoT security frameworks, offering adaptive, efficient, and reliable DDoS detection capabilities. These findings have shown the potential of machine learning in addressing the pressing need for robust IoT security solutions that can mitigate modern cyber threats and assure network integrity.

Mixtures of Experts (MoE) are Machine Learning models that involve partitioning the input space, with a separate "expert" model trained on each partition. Recently, MoE have become popular as components in today's large language models as a means to reduce training and inference costs. There, the partitioning function and the experts are both learnt jointly via gradient descent on the log-likelihood. In this paper we focus on studying the efficiency of the Expectation Maximization (EM) algorithm for the training of MoE models. We first rigorously analyze EM for the cases of linear or logistic experts, where we show that EM is equivalent to Mirror Descent with unit step size and a Kullback-Leibler Divergence regularizer. This perspective allows us to derive new convergence results and identify conditions for local linear convergence based on the signal-to-noise ratio (SNR). Experiments on synthetic and (small-scale) real-world data show that EM outperforms the gradient descent algorithm both in terms of convergence rate and the achieved accuracy.

Bilevel Optimization has experienced significant advancements recently with the introduction of new efficient algorithms. Mirroring the success in single-level optimization, stochastic gradient-based algorithms are widely used in bilevel optimization. However, a common limitation in these algorithms is the presumption of independent sampling, which can lead to increased computational costs due to the complicated hyper-gradient formulation of bilevel problems. To address this challenge, we study the example-selection strategy for bilevel optimization in this work. More specifically, we introduce a without-replacement sampling based algorithm which achieves a faster convergence rate compared to its counterparts that rely on independent sampling. Beyond the standard bilevel optimization formulation, we extend our discussion to conditional bilevel optimization and also two special cases: minimax and compositional optimization.

Stochastic simulation models are generative models that mimic complex systems to help with decision-making. The reliability of these models heavily depends on well-calibrated input model parameters. However, in many practical scenarios, only output-level data are available to learn the input model parameters, which is challenging due to the often intractable likelihood of the stochastic simulation model. Moreover, stochastic simulation models are frequently inexact, with discrepancies between the model and the target system. No existing methods can effectively learn and quantify the uncertainties of input parameters using only output-level data. In this paper, we propose to learn differentiable input parameters of stochastic simulation models using output-level data via kernel score minimization with stochastic gradient descent. We quantify the uncertainties of the learned input parameters using a frequentist confidence set procedure based on a new asymptotic normality result that accounts for model inexactness. The proposed method is evaluated on exact and inexact G/G/1 queueing models.

Optimization algorithms are pivotal in advancing various scientific and industrial fields but often encounter obstacles such as trapping in local minima, saddle points, and plateaus (flat regions), which makes the convergence to reasonable or near-optimal solutions particularly challenging. This paper presents the Steepest Perturbed Gradient Descent (SPGD), a novel algorithm that innovatively combines the principles of the gradient descent method with periodic uniform perturbation sampling to effectively circumvent these impediments and lead to better solutions whenever possible. SPGD is distinctively designed to generate a set of candidate solutions and select the one exhibiting the steepest loss difference relative to the current solution. It enhances the traditional gradient descent approach by integrating a strategic exploration mechanism that significantly increases the likelihood of escaping sub-optimal local minima and navigating complex optimization landscapes effectively. Our approach not only retains the directed efficiency of gradient descent but also leverages the exploratory benefits of stochastic perturbations, thus enabling a more comprehensive search for global optima across diverse problem spaces. We demonstrate the efficacy of SPGD in solving the 3D component packing problem, an NP-hard challenge. Preliminary results show a substantial improvement over four established methods, particularly on response surfaces with complex topographies and in multidimensional non-convex continuous optimization problems. Comparative analyses with established 2D benchmark functions highlight SPGD's superior performance, showcasing its ability to navigate complex optimization landscapes. These results emphasize SPGD's potential as a versatile tool for a wide range of optimization problems.

Neural networks trained with stochastic gradient descent exhibit an inductive bias towards simpler decision boundaries, typically converging to a narrow family of functions, and often fail to capture more complex features. This phenomenon raises concerns about the capacity of deep models to adequately learn and represent real-world datasets. Traditional approaches such as explicit regularization, data augmentation, architectural modifications, etc., have largely proven ineffective in encouraging the models to learn diverse features. In this work, we investigate the impact of pre-training models with noisy labels on the dynamics of SGD across various architectures and datasets. We show that pretraining promotes learning complex functions and diverse features in the presence of noise. Our experiments demonstrate that pre-training with noisy labels encourages gradient descent to find alternate minima that do not solely depend upon simple features, rather learns more complex and broader set of features, without hurting performance.

Logistic regression, the Support Vector Machine (SVM), and least squares are well-studied methods in the statistical and computer science community, with various practical applications. High-dimensional data arriving on a real-time basis makes the design of online learning algorithms that produce sparse solutions essential. The seminal work of \hyperlink{cite.langford2009sparse}{Langford, Li, and Zhang (2009)} developed a method to obtain sparsity via truncated gradient descent, showing a near-optimal online regret bound. Based on this method, we develop a quantum sparse online learning algorithm for logistic regression, the SVM, and least squares. Given efficient quantum access to the inputs, we show that a quadratic speedup in the time complexity with respect to the dimension of the problem is achievable, while maintaining a regret of $O(1/\sqrt{T})$, where $T$ is the number of iterations.

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the increasing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.

Animals survive in dynamic environments changing at arbitrary timescales, but such data distribution shifts are a challenge to neural networks. To adapt to change, neural systems may change a large number of parameters, which is a slow process involving forgetting past information. In contrast, animals leverage distribution changes to segment their stream of experience into tasks and associate them with internal task abstracts. Animals can then respond flexibly by selecting the appropriate task abstraction. However, how such flexible task abstractions may arise in neural systems remains unknown. Here, we analyze a linear gated network where the weights and gates are jointly optimized via gradient descent, but with neuron-like constraints on the gates including a faster timescale, nonnegativity, and bounded activity. We observe that the weights self-organize into modules specialized for tasks or sub-tasks encountered, while the gates layer forms unique representations that switch the appropriate weight modules (task abstractions). We analytically reduce the learning dynamics to an effective eigenspace, revealing a virtuous cycle: fast adapting gates drive weight specialization by protecting previous knowledge, while weight specialization in turn increases the update rate of the gating layer. Task switching in the gating layer accelerates as a function of curriculum block size and task training, mirroring key findings in cognitive neuroscience. We show that the discovered task abstractions support generalization through both task and subtask composition, and we extend our findings to a non-linear network switching between two tasks. Overall, our work offers a theory of cognitive flexibility in animals as arising from joint gradient descent on synaptic and neural gating in a neural network architecture.