Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- abstractJune 2024
Strategyproof Decision-Making in Panel Data Settings and Beyond
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 52, Issue 1Pages 69–70https://doi.org/10.1145/3673660.3655083We consider the problem of decision-making using panel data, in which a decision-maker gets noisy, repeated measurements of multiple units (or agents). We consider the setup used in synthetic control methods, where there is a pre-intervention period when ...
Also Published in:
SIGMETRICS/PERFORMANCE '24: Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems: ISBN 9798400706240 - abstractJune 2024
FedQV: Leveraging Quadratic Voting in Federated Learning
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 52, Issue 1Pages 91–92https://doi.org/10.1145/3673660.3655055Federated Learning (FL) permits different parties to collaboratively train a global model without disclosing their respective local labels. A crucial step of FL, that of aggregating local models to produce the global one, shares many similarities with ...
Also Published in:
SIGMETRICS/PERFORMANCE '24: Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems: ISBN 9798400706240 - abstractJune 2024
Automated Backend Allocation for Multi-Model, On-Device AI Inference
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 52, Issue 1Pages 27–28https://doi.org/10.1145/3673660.3655046On-Device Artificial Intelligence (AI) services such as face recognition, object tracking and voice recognition are rapidly scaling up deployments on embedded, memory-constrained hardware devices. These services typically delegate AI inference models for ...
Also Published in:
SIGMETRICS/PERFORMANCE '24: Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems: ISBN 9798400706240 - abstractJune 2024Best Paper
Agents of Autonomy: A Systematic Study of Robotics on Modern Hardware
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 52, Issue 1Pages 25–26https://doi.org/10.1145/3673660.3655043As robots increasingly permeate modern society, it is crucial for the system and hardware research community to bridge its long-standing gap with robotics. This divide has persisted due to the lack of (i) a systematic performance evaluation of robotics ...
Also Published in:
SIGMETRICS/PERFORMANCE '24: Abstracts of the 2024 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems: ISBN 9798400706240 - articleJanuary 2024
Data-Rich Causal Inference
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 51, Issue 3Pages 54–57https://doi.org/10.1145/3639830.3639851Brief Biography: Abhin Shah is a final-year Ph.D. student in the department of Electrical Engineering and Computer Science atMIT, where he is a recipient ofMIT's Jacobs Presidential Fellowship. He has interned with Google Research (2021) and IBM Research ...
-
- articleJanuary 2024
Enhancing Security and Privacy in Head-Mounted Augmented Reality Systems Using Eye Gaze
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 51, Issue 3Pages 42–45https://doi.org/10.1145/3639830.3639848Augmented Reality (AR) devices offer a rich, immersive experience that provides the user with a blend of the physical and the synthetic, digitally augmented world. This augmentation is made possible by the AR device's sensors, which are constantly ...
- articleJanuary 2024
Adaptivity, Structure, and Objectives in Sequential Decision-Making
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 51, Issue 3Pages 38–41https://doi.org/10.1145/3639830.3639846Sequential decision-making algorithms are ubiquitous in the design and optimization of large-scale systems due to their practical impact. The typical algorithmic paradigm ignores the sequential notion of these problems: use a historical dataset to ...
- articleJanuary 2024
Best Practices for Exoskeleton Evaluation Using DeepLabCut
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 51, Issue 3Pages 22–24https://doi.org/10.1145/3639830.3639840Exoskeleton fit evaluation using pose estimation is necessary to ensure exoskeletons promote productivity in industrial settings. However, both marker-based and markerless vision based systems consist of uncertainties in tracking human joints while a ...
- abstractJune 2023
Malcolm: Multi-agent Learning for Cooperative Load Management at Rack Scale
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 51, Issue 1Pages 39–40https://doi.org/10.1145/3606376.3593550We consider the problem of balancing the load among servers in dense racks for microsecond-scale workloads. To balance the load in such settings, tens of millions of scheduling decisions have to be made per second. Achieving this throughput while ...
Also Published in:
SIGMETRICS '23: Abstract Proceedings of the 2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems: ISBN 9798400700743 - abstractJuly 2022
Prediction of the Resource Consumption of Distributed Deep Learning Systems
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 50, Issue 1Pages 69–70https://doi.org/10.1145/3547353.3530962Predicting resource consumption for the distributed training of deep learning models is of paramount importance, as it can inform a priori users of how long their training would take and enable users to manage the cost of training. Yet, no such ...
Also Published in:
SIGMETRICS/PERFORMANCE '22: Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems: ISBN 9781450391412 - abstractJuly 2022
One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 50, Issue 1Pages 55–56https://doi.org/10.1145/3547353.3522631Convolutional neural networks (CNNs) are used in numerous realworld applications such as vision-based autonomous driving and video content analysis.
Also Published in:
SIGMETRICS/PERFORMANCE '22: Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems: ISBN 9781450391412 - abstractJune 2022
Revisiting Modified Greedy Algorithm for Monotone Submodular Maximization with a Knapsack Constraint
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 49, Issue 1Pages 63–64https://doi.org/10.1145/3543516.3453925Monotone submodular maximization with a knapsack constraint is NP-hard. Various approximation algorithms have been devised to address this optimization problem. In this paper, we revisit the widely known modified greedy algorithm. First, we show that ...
Also Published in:
SIGMETRICS '21: Abstract Proceedings of the 2021 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems: ISBN 9781450380720 - keynoteJune 2022
AI for System - Infusing AI into Cloud Computing Systems
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 49, Issue 1Pages 39–40https://doi.org/10.1145/3543516.3453911In the past fifteen years, the most significant paradigm shift in the computing industry is the migration to cloud computing, which brings unprecedented opportunities of digital transformation to business, society, and human life. The implication of ...
Also Published in:
SIGMETRICS '21: Abstract Proceedings of the 2021 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems: ISBN 9781450380720 - keynoteJune 2022
Opening the Black Box of Deep Learning: Some Lessons and Take-aways
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 49, Issue 1Page 1https://doi.org/10.1145/3543516.3453910Deep learning has rapidly come to dominate AI and machine learning in the past decade. These successes have come despite deep learning largely being a "black box." A small subdiscipline has grown up trying to derive better understanding of the ...
Also Published in:
SIGMETRICS '21: Abstract Proceedings of the 2021 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems: ISBN 9781450380720 - research-articleJuly 2020
Logarithmic Communication for Distributed Optimization in Multi-Agent Systems
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 48, Issue 1Pages 97–98https://doi.org/10.1145/3410048.3410105Classically, the design of multi-agent systems is approached using techniques from distributed optimization such as dual descent and consensus algorithms. Such algorithms depend on convergence to global consensus before any individual agent can ...
- research-articleJuly 2020
Non-Asymptotic Analysis of Monte Carlo Tree Search
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 48, Issue 1Pages 31–32https://doi.org/10.1145/3410048.3410066In this work, we consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of infinite-horizon discounted cost Markov Decision Process (MDP) with deterministic ...
- research-articleJune 2018
Hound: Causal Learning for Datacenter-scale Straggler Diagnosis
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 46, Issue 1Pages 59–61https://doi.org/10.1145/3292040.3219641Stragglers are exceptionally slow tasks within a job that delay its completion. Stragglers, which are uncommon within a single job, are pervasive in datacenters with many jobs. We present Hound, a statistical machine learning framework that infers the ...
Also Published in:
SIGMETRICS '18: Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems: ISBN 9781450358460 - short-paperSeptember 2015
Learning Optimal Policies in Markov Decision Processes with Value Function Discovery?
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 43, Issue 2Pages 7–9https://doi.org/10.1145/2825236.2825239In this paper we describe recent progress in our work on Value Function Discovery (vfd), a novel method for discovery of value functions for Markov Decision Processes (mdps). In a previous paper we described how vfd discovers algebraic descriptions of ...
- research-articleJune 2014
Stochastic bandits with side observations on networks
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 42, Issue 1Pages 289–300https://doi.org/10.1145/2637364.2591989We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions. In our model, choosing an action provides additional side observations for a subset of the remaining actions. One example of this model occurs ...
Also Published in:
SIGMETRICS '14: The 2014 ACM international conference on Measurement and modeling of computer systems: ISBN 9781450327893 - short-paperJanuary 2014
Real-time deferrable load control: handling the uncertainties of renewable generation
ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS), Volume 41, Issue 3Pages 77–79https://doi.org/10.1145/2567529.2567553Real-time demand response is potential to handle the uncertainties of renewable generation. It is expected that a large number of deferrable loads, including electric vehicles and smart appliances, will participate in demand response in the future. In ...