Bingcong Li's research while affiliated with University of Minnesota Duluth and other places

Publications (22)

Preprint
Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. By succinctly encoding local graph structures and features of nodes, state-of-the-art GNNs can scale linearly with the size of grap...
Preprint
Full-text available
Conditional gradient, aka Frank Wolfe (FW) algorithms, have well-documented merits in machine learning and signal processing applications. Unlike projection-based methods, momentum cannot improve the convergence rate of FW, in general. This limitation motivates the present work, which deals with heavy ball momentum, and its impact to FW. Specifical...
Article
Full-text available
With the well-documented popularity of Frank Wolfe (FW) algorithms in machine learning tasks, the present paper establishes links between FW subproblems and the notion of momentum emerging in accelerated gradient methods (AGMs). On the one hand, these links reveal why momentum is unlikely to be effective for FW-type algorithms on general problems....
Article
Aiming at convex optimization under structural constraints, this work introduces and analyzes a variant of the Frank Wolfe (FW) algorithm termed ExtraFW. The distinct feature of ExtraFW is the pair of gradients leveraged per iteration, thanks to which the decision variable is updated in a prediction-correction (PC) format. Relying on no problem dep...
Article
This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: contexts and side observations. In this setting, a learning agent repeatedly chooses from a set of K actions after being presented with a d-dimensional context vector. The ag...
Preprint
This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: \emph{contexts} and \emph{side observations}. In this setting, a learning agent repeatedly chooses from a set of $K$ actions after being presented with a $d$-dimensional cont...
Preprint
Full-text available
Aiming at convex optimization under structural constraints, this work introduces and analyzes a variant of the Frank Wolfe (FW) algorithm termed ExtraFW. The distinct feature of ExtraFW is the pair of gradients leveraged per iteration, thanks to which the decision variable is updated in a prediction-correction (PC) format. Relying on no problem dep...
Preprint
We unveil the connections between Frank Wolfe (FW) type algorithms and the momentum in Accelerated Gradient Methods (AGM). On the negative side, these connections illustrate why momentum is unlikely to be effective for FW type algorithms. The encouraging message behind this link, on the other hand, is that momentum is useful for FW on a class of pr...
Article
To accommodate heterogeneous tasks for the Internet of Things (IoT), the emerging mobile edge paradigm extends computing services from the cloud to the edge, but at the same time exposes new challenges on security. In this context, the present paper deals with online security-aware edge computing under jamming attacks. Leveraging online learning to...
Preprint
The main goal of this work is equipping convex and nonconvex problems with Barzilai-Borwein (BB) step size. With the adaptivity of BB step sizes granted, they can fail when the objective function is not strongly convex. To overcome this challenge, the key idea here is to bridge (non)convex problems and strongly convex ones via regularization. The p...
Preprint
Cascading bandit (CB) is a variant of both the multi-armed bandit (MAB) and the cascade model (CM), where a learning agent aims to maximize the total reward by recommending $K$ out of $L$ items to a user. We focus on a common real-world scenario where the user's preference can change in a piecewise-stationary manner. Two efficient algorithms, \text...
Preprint
The variance reduction class of algorithms including the representative ones, abbreviated as SVRG and SARAH, have well documented merits for empirical risk minimization tasks. However, they require grid search to optimally tune parameters (step size and the number of iterations per inner loop) for best performance. This work introduces `almost tune...
Preprint
The main theme of this work is a unifying algorithm, abbreviated as L2S, that can deal with (strongly) convex and nonconvex empirical risk minimization (ERM) problems. It broadens a recently developed variance reduction method known as SARAH. L2S enjoys a linear convergence rate for strongly convex problems, which also implies the last iteration of...
Preprint
The present paper considers leveraging network topology information to improve the convergence rate of ADMM for decentralized optimization, where networked nodes work collaboratively to minimize the objective. Such problems can be solved efficiently using ADMM via decomposing the objective into easier subproblems. Properly exploiting network topolo...
Preprint
This paper studies bandit learning problems with delayed feedback, which included multi-armed bandit (MAB) and bandit convex optimization (BCO). Given only function value information (a.k.a. bandit feedback), algorithms for both MAB and BCO typically rely on (possibly randomized) gradient estimators based on function values, and then feed them into...
Preprint
Full-text available
To accommodate heterogeneous tasks in Internet of Things (IoT), a new communication and computing paradigm termed mobile edge computing emerges that extends computing services from the cloud to edge, but at the same time exposes new challenges on security. The present paper studies online security-aware edge computing under jamming attacks. Leverag...
Article
Full-text available
Energy storage units hold promise to transform the electric power industry, since they can supply power to end customers during peak demand times, and operate as customers upon a power surplus. The present paper studies online energy management with renewable energy resources and energy storage units. For the problem at hand, the popular approaches...

Citations

... To analyze convergence of FW iterations, it is reasonable to rely on the position of the optimal solution, which justifies why this assumption is also adopted in [19], [26], [42], [43]. For a number of signal processing and machine learning tasks, Assumption 4 is rather mild. ...
... The height of the camera stand is 1 m and 2.3 m, respectively, and the angle is 15°downward. The experimental data can be referred to in the reference (Dhiman and Kumar, 2017;Li et al., 2021;Traoré and Pauwels, 2021;Xu et al., 2021). During the training phase, the base learning rate was .00001, the weight decay was .00005, the batch size was 64, and the momentum was .9. ...
... We also implemented acceleration techniques such as averaging gradients [49] and away steps [46], [50], but did not observe practical gains compared to the vanilla FW. Moreover, while it is common practice to use entropic or other strongly-convex regularizations in OT to facilitate producing the atom solutions, we did not incorporate such regularizations because an atom solution can be produced easily in our formulation. ...
... Third, they can be scaled to construct accelerated second order methods [41] and accelerated higher order methods [42]. Lastly, they have been shown to excel in performance even when they have been extended to other settings such as distributed optimization [43], nonconvex optimization [44], stochastic optimization [45], non-Euclidean optimization [46], [47], etc. In [48], it is argued that the key behind constructing optimal methods lies in the accumulation of some global information on the objective function. ...
... An online combinatorial bandit upper confidence bound algorithm was proposed in [19] for the task scheduling to asymptotically minimize the computing delay. The security-aware server selection strategies based on MAB were reported in [20]. The MAB-based task offloading approach was further adapted to the vehicular edge computing systems in [21]. ...
... By deploying a UAV-assisted MEC system, end devices can efficiently complete delay-sensitive applications. In [14][15][16][17][18][19][20], the secure data offloading mechanisms were investigated along with the research on UAV-assisted MEC systems [21][22][23][24]. Physical layer security has become one of the constraints when data offloading occurs in the MEC system. ...
... Presentation of performance is done. It provides low power access protocol for mobile and wireless ATM networks [ Li B., et al(2017)]. In this paper the information about the ATM users are analyzed and sensed using pyroelectric infrared sensors (PIR). ...
... Reference [19] considered the seasonality of wind turbine output and constructed an optimization model for the wind/solar/storage microgrid system. ...