Adding bibtex ref of SLearn (Cluster Scheduler) papers in bibliograph…

bibliography.bib

@@ -176,8 +176,6 @@ @InProceedings{clusterdata:Reiss2012
 If you just want one citation about the Cluster2011 trace, then
 use \cite{clusterdata:Reiss2012b}.
 
-
-
 ################ 2022
 @inproceedings {clusterdata:jajooSLearn2022,
 author = {Akshay Jajoo and Y. Charlie Hu and Xiaojun Lin and Nan Deng},
@@ -617,6 +615,113 @@ @Article{clusterdata:Mishra2010
 use the traces as inputs, e.g., in simulations or load predictions.
 Order: most recent first.
 
+################ 2023
+@ARTICLE{clusterdata:jajooSLearnTCC2023,
+  author={Jajoo, Akshay and Hu, Y. Charlie and Lin, Xiaojun and Deng, Nan},
+  journal={IEEE Transactions on Cloud Computing}, 
+  title={SLearn: A Case for Task Sampling Based Learning for Cluster Job Scheduling}, 
+  year={2023},
+  volume={11},
+  number={3},
+  pages={2664-2680},
+  publisher = {USENIX Association},
+  keywords = {data centers, big data, job scheduling, learning, online learning},
+  abstract = {The ability to accurately estimate job runtime properties allows a 
+	scheduler to effectively schedule jobs. State-of-the-art online cluster 
+	job schedulers use history-based learning, which uses past job execution 
+	information to estimate the runtime properties of newly arrived jobs. 
+	However, with fast-paced development in cluster technology (in both hardware
+	and software) and changing user inputs, job runtime properties can change over 
+	time, which lead to inaccurate predictions. In this article, we explore the 
+	potential and limitation of real-time learning of job runtime properties, 
+	by proactively sampling and scheduling a small fraction of the tasks of 
+	each job. Such a task-sampling-based approach exploits the similarity among 
+	runtime properties of the tasks of the same job and is inherently immune to 
+	changing job behavior. Our analytical and experimental analysis of 3 production
+	traces with different skew and job distribution shows that learning in space can
+	be substantially more accurate. Our simulation and testbed evaluation on Azure of 
+	the two learning approaches anchored in a generic job scheduler using 3 production
+	cluster job traces shows that despite its online overhead, learning in space reduces
+	the average Job Completion Time (JCT) by 1.28×, 1.56×, and 1.32× compared to the 
+	prior-art history-based predictor. We further analyze the experimental results to 
+	give intuitive explanations to why learning in space outperforms learning in time 
+	in these experiments. Finally, we show how sampling-based learning can be extended 
+	to schedule DAG jobs and achieve similar speedups over the prior-art history-based 
+	predictor.},
+  doi={10.1109/TCC.2022.3222649}}
+
+
+################ 2022
+@inproceedings {clusterdata:jajooSLearnNSDI2022,
+author = {Akshay Jajoo and Y. Charlie Hu and Xiaojun Lin and Nan Deng},
+title = {A Case for Task Sampling based Learning for Cluster Job Scheduling},
+booktitle = {19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)},
+year = {2022},
+address = {Renton, WA, USA},
+url = {https://www.usenix.org/conference/nsdi22/presentation/jajoo},
+publisher = {USENIX Association},
+keywords = {data centers, big data, job scheduling, learning, online learning},
+abstract = {The ability to accurately estimate job runtime properties allows a
+  scheduler to effectively schedule jobs. State-of-the-art online cluster job 
+  schedulers use history-based learning, which uses past job execution information 
+  to estimate the runtime properties of newly arrived jobs. However, with fast-paced
+  development in cluster technology (in both hardware and software) and changing user
+  inputs, job runtime properties can change over time, which lead to inaccurate predictions.
+  In this paper, we explore the potential and limitation of real-time learning of job 
+  runtime properties, by proactively sampling and scheduling a small fraction of the
+  tasks of each job. Such a task-sampling-based approach exploits the similarity among
+  runtime properties of the tasks of the same job and is inherently immune to changing
+  job behavior. Our study focuses on two key questions in comparing task-sampling-based
+  learning (learning in space) and history-based learning (learning in time): (1) Can
+  learning in space be more accurate than learning in time? (2) If so, can delaying
+  scheduling the remaining tasks of a job till the completion of sampled tasks be more
+  than compensated by the improved accuracy and result in improved job performance? Our
+  analytical and experimental analysis of 3 production traces with different skew and job
+  distribution shows that learning in space can be substantially more accurate. Our 
+  simulation and testbed evaluation on Azure of the two learning approaches anchored in a
+  generic job scheduler using 3 production cluster job traces shows that despite its online
+  overhead, learning in space reduces the average Job Completion Time (JCT) by 1.28x, 1.56x,
+  and 1.32x compared to the prior-art history-based predictor.},
+}
+
+
+################ 2021
+@article{clusterdata:jajooSLearnTechReport2021,
+  author    = {Akshay Jajoo and Y. Charlie Hu and Xiaojun Lin and Nan Deng},
+  title     = {The Case for Task Sampling based Learning for Cluster Job Scheduling},
+  journal   = {Computing Research Repository},
+  volume    = {abs/2108.10464},
+  year      = {2021},
+  url       = {https://arxiv.org/abs/2108.10464},
+  eprinttype = {arXiv},
+  eprint    = {2108.10464},
+  timestamp = {Fri, 27 Aug 2021 15:02:29 +0200},
+  biburl    = {https://dblp.org/rec/journals/corr/abs-2108-10464.bib},
+  bibsource = {dblp computer science bibliography, https://dblp.org},
+  keywords = {data centers, big data, job scheduling, learning, online learning},
+  abstract = {The ability to accurately estimate job runtime properties allows a
+    scheduler to effectively schedule jobs. State-of-the-art online cluster job 
+    schedulers use history-based learning, which uses past job execution information 
+    to estimate the runtime properties of newly arrived jobs. However, with fast-paced
+    development in cluster technology (in both hardware and software) and changing user
+    inputs, job runtime properties can change over time, which lead to inaccurate predictions.
+    In this paper, we explore the potential and limitation of real-time learning of job 
+    runtime properties, by proactively sampling and scheduling a small fraction of the
+    tasks of each job. Such a task-sampling-based approach exploits the similarity among
+    runtime properties of the tasks of the same job and is inherently immune to changing
+    job behavior. Our study focuses on two key questions in comparing task-sampling-based
+    learning (learning in space) and history-based learning (learning in time): (1) Can
+    learning in space be more accurate than learning in time? (2) If so, can delaying
+    scheduling the remaining tasks of a job till the completion of sampled tasks be more
+    than compensated by the improved accuracy and result in improved job performance? Our
+    analytical and experimental analysis of 3 production traces with different skew and job
+    distribution shows that learning in space can be substantially more accurate. Our 
+    simulation and testbed evaluation on Azure of the two learning approaches anchored in a
+    generic job scheduler using 3 production cluster job traces shows that despite its online
+    overhead, learning in space reduces the average Job Completion Time (JCT) by 1.28x, 1.56x,
+    and 1.32x compared to the prior-art history-based predictor.},
+}
+
 ################ 2020
 
 @INPROCEEDINGS{clusterdata:Lin2020,