Gary Boudreau

Roghayeh Joda, Medhat Elsayed, Hatem Abou-zeid et al.

The Internet of Senses (IoS) holds the promise of flawless telepresence-style communication for all human `receptors' and therefore blurs the difference of virtual and real environments. We commence by highlighting the compelling use cases empowered by the IoS and also the key network requirements. We then elaborate on how the emerging semantic communications and Artificial Intelligence (AI)/Machine Learning (ML) paradigms along with 6G technologies may satisfy the requirements of IoS use cases. On one hand, semantic communications can be applied for extracting meaningful and significant information and hence efficiently exploit the resources and for harnessing a priori information at the receiver to satisfy IoS requirements. On the other hand, AI/ML facilitates frugal network resource management by making use of the enormous amount of data generated in IoS edge nodes and devices, as well as by optimizing the IoS performance via intelligent agents. However, the intelligent agents deployed at the edge are not completely aware of each others' decisions and the environments of each other, hence they operate in a partially rather than fully observable environment. Therefore, we present a case study of Partially Observable Markov Decision Processes (POMDP) for improving the User Equipment (UE) throughput and energy consumption, as they are imperative for IoS use cases, using Reinforcement Learning for astutely activating and deactivating the component carriers in carrier aggregation. Finally, we outline the challenges and open issues of IoS implementations and employing semantic communications, edge intelligence as well as learning under partial observability in the IoS context.

Ali Bereyhi, Ben Liang, Gary Boudreau et al.

Error accumulation is an essential component of the Top-$k$ sparsification method in distributed gradient descent. It implicitly scales the learning rate and prevents the slow-down of lateral movement, but it can also deteriorate convergence. This paper proposes a novel sparsification algorithm called regularized Top-$k$ (RegTop-$k$) that controls the learning rate scaling of error accumulation. The algorithm is developed by looking at the gradient sparsification as an inference problem and determining a Bayesian optimal sparsification mask via maximum-a-posteriori estimation. It utilizes past aggregated gradients to evaluate posterior statistics, based on which it prioritizes the local gradient entries. Numerical experiments with ResNet-18 on CIFAR-10 show that at $0.1\%$ sparsification, RegTop-$k$ achieves about $8\%$ higher accuracy than standard Top-$k$.

Hussein A. Ammar, Raviraj Adve, Shahram Shahbazpanahi et al.

In the user-centric cell-free massive MIMO (UC-mMIMO) network scheme, user mobility necessitates updating the set of serving access points to maintain the user-centric clustering. Such updates are typically performed through handoff (HO) operations; however, frequent HOs lead to overheads associated with the allocation and release of resources. This paper presents a deep reinforcement learning (DRL)-based solution to predict and manage these connections for mobile users. Our solution employs the Soft Actor-Critic algorithm, with continuous action space representation, to train a deep neural network to serve as the HO policy. We present a novel proposition for a reward function that integrates a HO penalty in order to balance the attainable rate and the associated overhead related to HOs. We develop two variants of our system; the first one uses mobility direction-assisted (DA) observations that are based on the user movement pattern, while the second one uses history-assisted (HA) observations that are based on the history of the large-scale fading (LSF). Simulation results show that our DRL-based continuous action space approach is more scalable than discrete space counterpart, and that our derived HO policy automatically learns to gather HOs in specific time slots to minimize the overhead of initiating HOs. Our solution can also operate in real time with a response time less than 0.4 ms.

Ali Bereyhi, Ben Liang, Gary Boudreau et al.

Error accumulation is effective for gradient sparsification in distributed settings: initially-unselected gradient entries are eventually selected as their accumulated error exceeds a certain level. The accumulation essentially behaves as a scaling of the learning rate for the selected entries. Although this property prevents the slow-down of lateral movements in distributed gradient descent, it can deteriorate convergence in some settings. This work proposes a novel sparsification scheme that controls the learning rate scaling of error accumulation. The development of this scheme follows two major steps: first, gradient sparsification is formulated as an inverse probability (inference) problem, and the Bayesian optimal sparsification mask is derived as a maximum-a-posteriori estimator. Using the prior distribution inherited from Top-$k$, we derive a new sparsification algorithm which can be interpreted as a regularized form of Top-$k$. We call this algorithm regularized Top-$k$ (RegTop-$k$). It utilizes past aggregated gradients to evaluate posterior statistics of the next aggregation. It then prioritizes the local accumulated gradient entries based on these posterior statistics. We validate our derivation through numerical experiments. In distributed linear regression, it is observed that while Top-$k$ remains at a fixed distance from the global optimum, RegTop-$k$ converges to the global optimum at significantly higher compression ratios. We further demonstrate the generalization of this observation by employing RegTop-$k$ in distributed training of ResNet-18 on CIFAR-10, where it noticeably outperforms Top-$k$.

Juncheng Wang, Ben Liang, Min Dong et al.

We consider online convex optimization (OCO) with multi-slot feedback delay, where an agent makes a sequence of online decisions to minimize the accumulation of time-varying convex loss functions, subject to short-term and long-term constraints that are possibly time-varying. The current convex loss function and the long-term constraint function are revealed to the agent only after the decision is made, and they may be delayed for multiple time slots. Existing work on OCO under this general setting has focused on the static regret, which measures the gap of losses between the online decision sequence and an offline benchmark that is fixed over time. In this work, we consider both the static regret and the more practically meaningful dynamic regret, where the benchmark is a time-varying sequence of per-slot optimizers. We propose an efficient algorithm, termed Delay-Tolerant Constrained-OCO (DTC-OCO), which uses a novel constraint penalty with double regularization to tackle the asynchrony between information feedback and decision updates. We derive upper bounds on its dynamic regret, static regret, and constraint violation, proving them to be sublinear under mild conditions. We further apply DTC-OCO to a general network resource allocation problem, which arises in many systems such as data networks and cloud computing. Simulation results demonstrate substantial performance gain of DTC-OCO over the known best alternative.