arXiv subjects

Mahsa Sahebdel

Publications and source records attributed to Mahsa Sahebdel.

7 recordsLinked to original sources

arXiv2025

Smoothed Online Optimization for Target Tracking: Robust and Learning-Augmented Algorithms

We introduce the Smoothed Online Optimization for Target Tracking (SOOTT) problem, a new framework that integrates three key objectives in online decision-making under uncertainty: (1) tracking cost for following a dynamically moving target, (2) adversarial perturbation cost for withstanding unpredictable disturbances, and (3) switching cost for penalizing abrupt changes in decisions. This formulation captures real-world scenarios such as elastic and inelastic workload scheduling in AI clusters, where operators must balance long-term service-level agreements (e.g., LLM training) against sudden demand spikes (e.g., real-time inference). We first present BEST, a robust algorithm with provable competitive guarantees for SOOTT. To enhance practical performance, we introduce CoRT, a learning-augmented variant that incorporates untrusted black-box predictions (e.g., from ML models) into its decision process. Our theoretical analysis shows that CoRT strictly improves over BEST when predictions are accurate, while maintaining robustness under arbitrary prediction errors. We validate our approach through a case study on workload scheduling, demonstrating that both algorithms effectively balance trajectory tracking, decision smoothness, and resilience to external disturbances.

cs.LG↗

arXiv2024

Near-Optimal Emission-Aware Online Ride Assignment Algorithm for Peak Demand Hours

Ridesharing has experienced significant global growth over the past decade and is becoming an integral component of modern transportation systems. However, despite their benefits, ridesharing platforms face fundamental inefficiencies that contribute to negative environmental impacts. A prominent source of such inefficiency is the deadhead miles. This issue becomes especially severe during high-demand periods, when the volume of ride requests exceeds the available driver supply, leading to suboptimal rider-to-driver assignments, longer deadhead trips, and increased emissions. Although limiting these unproductive miles can reduce emissions, doing so may increase passenger wait times due to limited driver availability, thereby degrading the overall service experience. In this paper, we introduce LARA, an online rider-to-driver assignment algorithm that dynamically adjusts the maximum allowable distance between rider and drivers and assigns ride requests accordingly. While LARA is applicable in general settings, it is particularly effective during peak demand periods, achieving reductions in both emissions and wait times. We provide theoretical guarantees showing that LARA achieves near-optimal performance in online environments, with respect to an optimal offline benchmark. Beside our theoretical analysis, our empirical evaluations on both synthetic and real-world datasets show that LARA achieves up to a 34% reduction in carbon emissions and up to a 50% decrease in rider wait times, compared to state-of-the-art baselines. While prior work has explored emission-aware ride assignment, LARA is, to our knowledge, the first algorithm to offer both rigorous theoretical guarantees and strong empirical performance.

eess.SY↗

arXiv2024

LEAD: Towards Learning-Based Equity-Aware Decarbonization in Ridesharing Platforms

Ridesharing platforms such as Uber, Lyft, and DiDi have grown in popularity due to their on-demand availability, ease of use, and commute cost reductions, among other benefits. However, not all ridesharing promises have panned out. Recent studies demonstrate that the expected drop in traffic congestion and reduction in greenhouse gas (GHG) emissions have not materialized. This is primarily due to the substantial distances traveled by the ridesharing vehicles without passengers between rides, known as deadhead miles. Recent work has focused on reducing the impact of deadhead miles while considering additional metrics such as rider waiting time, GHG emissions from deadhead miles, or driver earnings. However, most prior studies consider these environmental and equity-based metrics individually despite them being interrelated. In this paper, we propose a Learning-based Equity-Aware Decarabonization approach, LEAD, for ridesharing platforms. LEAD targets minimizing emissions while ensuring that the driver's utility, defined as the difference between the trip distance and the deadhead miles, is fairly distributed. LEAD uses reinforcement learning to match riders with drivers based on the expected future utility of drivers and the expected carbon emissions of the platform without increasing the rider waiting times. Extensive experiments based on a real-world ridesharing dataset show that LEAD improves the defined notion of fairness by 150% when compared to emission-aware ride-assignment and reduces emissions by 14.6% while ensuring fairness within 28--52% of the fairness-focused baseline. It also reduces the rider wait time, by at least 32.1%, compared to a fairness-focused baseline.

eess.SY↗

arXiv2024

A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments

Training a model-free reinforcement learning agent requires allowing the agent to sufficiently explore the environment to search for an optimal policy. In safety-constrained environments, utilizing unsupervised exploration or a non-optimal policy may lead the agent to undesirable states, resulting in outcomes that are potentially costly or hazardous for both the agent and the environment. In this paper, we introduce a new exploration framework for navigating the grid environments that enables model-free agents to interact with the environment while adhering to safety constraints. Our framework includes a pre-training phase, during which the agent learns to identify potentially unsafe states based on both observable features and specified safety constraints in the environment. Subsequently, a binary classification model is trained to predict those unsafe states in new environments that exhibit similar dynamics. This trained classifier empowers model-free agents to determine situations in which employing random exploration or a suboptimal policy may pose safety risks, in which case our framework prompts the agent to follow a predefined safe policy to mitigate the potential for hazardous consequences. We evaluated our framework on three randomly generated grid environments and demonstrated how model-free agents can safely adapt to new tasks and learn optimal policies for new environments. Our results indicate that by defining an appropriate safe policy and utilizing a well-trained model to detect unsafe states, our framework enables a model-free agent to adapt to new tasks and environments with significantly fewer safety violations.

cs.AI↗

arXiv2024

A Holistic Approach for Equity-aware Carbon Reduction of Ridesharing Platforms

Ridesharing services have revolutionized personal mobility, offering convenient on-demand transportation anytime. While early proponents of ridesharing suggested that these services would reduce the overall carbon emissions of the transportation sector, recent studies reported a type of rebound effect showing substantial carbon emissions of ridesharing platforms, mainly due to their deadhead miles traveled between two consecutive rides. However, reducing deadhead miles' emissions can incur longer waiting times for riders and starvation of ride assignments for some drivers. Therefore, any efforts towards reducing the carbon emissions from ridesharing platforms must consider the impact on the quality of service, e.g., waiting time, and on the equitable distribution of rides across drivers. This paper proposes a holistic approach to reduce the carbon emissions of ridesharing platforms while minimizing the degradation in user waiting times and equitable ride assignments across drivers. Towards this end, we decompose the global carbon reduction problem into two sub-problems: carbon- and equity-aware ride assignment and fuel-efficient routing. For the ride assignment problem, we consider the trade-off between the amount of carbon reduction and the rider's waiting time and propose simple yet efficient algorithms to handle the conflicting trade-offs. For the routing problem, we analyze the impact of fuel-efficient routing in reducing the carbon footprint, trip duration, and driver efficiency of ridesharing platforms using route data from Google Maps. Our comprehensive trace-driven experimental results show significant emissions reduction with a minor increase in riders' waiting times. Finally, we release E$^2$-RideKit, a toolkit that enables researchers to augment ridesharing datasets with emissions and equity information for further research on emission analysis and platform improvement.

eess.SY↗

arXiv2023

BOLA360: Near-optimal View and Bitrate Adaptation for 360-degree Video Streaming

Recent advances in omnidirectional cameras and AR/VR headsets have spurred the adoption of 360-degree videos that are widely believed to be the future of online video streaming. 360-degree videos allow users to wear a head-mounted display (HMD) and experience the video as if they are physically present in the scene. Streaming high-quality 360-degree videos at scale is an unsolved problem that is more challenging than traditional (2D) video delivery. The data rate required to stream 360-degree videos is an order of magnitude more than traditional videos. Further, the penalty for rebuffering events where the video freezes or displays a blank screen is more severe as it may cause cybersickness. We propose an online adaptive bitrate (ABR) algorithm for 360-degree videos called BOLA360 that runs inside the client's video player and orchestrates the download of video segments from the server so as to maximize the quality-of-experience (QoE) of the user. BOLA360 conserves bandwidth by downloading only those video segments that are likely to fall within the field-of-view (FOV) of the user. In addition, BOLA360 continually adapts the bitrate of the downloaded video segments so as to enable a smooth playback without rebuffering. We prove that BOLA360 is near-optimal with respect to an optimal offline algorithm that maximizes QoE. Further, we evaluate BOLA360 on a wide range of network and user head movement profiles and show that it provides $13.6\%$ to $372.5\%$ more QoE than state-of-the-art algorithms. While ABR algorithms for traditional (2D) videos have been well-studied over the last decade, our work is the first ABR algorithm for 360-degree videos with both theoretical and empirical guarantees on its performance.

cs.MM↗

arXiv2020

TeleCrowd: A Crowdsourcing Approach to Create Informal to Formal Text Corpora

Crowdsourcing has been widely used recently as an alternative to traditional annotations that is costly and usually done by experts. However, crowdsourcing tasks are not interesting by themselves, therefore, combining tasks with game will increase both participants motivation and engagement. In this paper, we have proposed a gamified crowdsourcing platform called TeleCrowd based on Telegram Messenger to use its social power as a base platform and facilitator for accomplishing crowdsourcing projects. Furthermore, to evaluate the performance of the proposed platform, we ran an experimental crowdsourcing project consisting of 500 informal Persian sentences in which participants were supposed to provide candidates that were the formal equivalent of sentences or qualify other candidates by upvoting or downvoting them. In this study, 2700 candidates and 21000 votes were submitted by the participants and a parallel dataset using candidates with the highest points, sum of their upvotes and downvotes, as the best candidates was built. As the evaluation, BLEU score of 0.54 was achieved on the collected dataset which shows that our proposed platform can be used to create large corpora. Also, this platform is highly efficient in terms of time period and cost price in comparison with other related works, because the whole duration of the project was 28 days at a cost of 40 dollars.

cs.SI↗