Avani Wildani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Avani Wildani has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
Ethan L. Miller
University of California, MS, Santa Cruz
9 shared publicationsIan F. Adams
6 shared publications- Jianzhao Bi
Department of Environmental and Occupational Health Sciences, University of Washington, Seattle, WA, USA
4 shared publications - Yang Liu
Central South University
3 shared publications Brian A. Madden
2 shared publications- Darrell D. E. Long
University of California, Santa Cruz, Santa Cruz, CA, USA
2 shared publications
Latest Publications
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 535-542
Rethinking Web Cache Design for the AI Era
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 535-542
Open AccessRethinking Web Cache Design for the AI Era
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 543-556
Valet: Efficient Data Placement on Modern SSDs
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 543-556
Open AccessValet: Efficient Data Placement on Modern SSDs
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1464-1477
Beyond Guess and Check: Quantifying the Fidelity of Proxy Applications
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1464-1477
Open AccessBeyond Guess and Check: Quantifying the Fidelity of Proxy Applications
- Open Access
- 20 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 213-222
Rethinking the Networking Stack for Serverless Environments: A Sidecar Approach
Serverless platforms rely on legacy networking stacks for communication and data movement. We quantitatively analyze the performance of these stacks and show their mismatch with highly consolidated, virtualized modern serverless environments, focusing on Firecracker, the most common serverless virtualization framework. As serverless applications grow in complexity and interaction, the resulting network bottleneck is a prime source of user-perceived, end-to-end latency. In this paper, we present a detailed vision of a new, sidecar-based networking stack for serverless environments. Our primary design goal is to provide low-overhead networking while maintaining existing security guarantees. We outline the research challenges in both the control and the data plane that the community needs to tackle before such a sidecar architecture can be used in practice.
- 20 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 213-222
Open AccessRethinking the Networking Stack for Serverless Environments: A Sidecar Approach
Serverless platforms rely on legacy networking stacks for communication and data movement. We quantitatively analyze the performance of these stacks and show their mismatch with highly consolidated, virtualized modern serverless environments, focusing on Firecracker, the most common serverless virtualization framework. As serverless applications grow in complexity and interaction, the resulting network bottleneck is a prime source of user-perceived, end-to-end latency. In this paper, we present a detailed vision of a new, sidecar-based networking stack for serverless environments. Our primary design goal is to provide low-overhead networking while maintaining existing security guarantees. We outline the research challenges in both the control and the data plane that the community needs to tackle before such a sidecar architecture can be used in practice.
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 6-10
PreSight: A Vision for an Instantaneous Web
We present the position that the time for general, scalable, privacy-preserving web cache speculation is at hand. At its core, web speculation is about predicting what resources users will want. Machine learning (ML) seems like a natural fit for this predictive task. We show, however, that ML is not fundamentally necessary to achieve a ~10% performance improvement worldwide across a diverse set of sites. We also present a set of constraints that large-scale CDNs are subject to, how these constraints limit the possibilities of using ML, what we did instead to achieve our performance results, and a discussion on the place of ML in large, Internet-scale, systems.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 6-10
Open AccessPreSight: A Vision for an Instantaneous Web
We present the position that the time for general, scalable, privacy-preserving web cache speculation is at hand. At its core, web speculation is about predicting what resources users will want. Machine learning (ML) seems like a natural fit for this predictive task. We show, however, that ML is not fundamentally necessary to achieve a ~10% performance improvement worldwide across a diverse set of sites. We also present a set of constraints that large-scale CDNs are subject to, how these constraints limit the possibilities of using ML, what we did instead to achieve our performance results, and a discussion on the place of ML in large, Internet-scale, systems.
- 22 August 2024
- Published by Springer Nature
- p. 385-400
Spatial Transfer Learning for Estimating PM$_{2.5}$ in Data-Poor Regions- 22 August 2024
- Published by Springer Nature
- p. 385-400
Spatial Transfer Learning for Estimating PM$_{2.5}$ in Data-Poor Regions- Open Access
- 23 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 23-30
Persistent Memory Research in the Post-Optane Era
After over a decade of researcher anticipation for the arrival of persistent memory (PMem), the first shipments of 3D XPoint-based Intel Optane Memory in 2019 were quickly followed by its cancellation in 2022. Was this another case of an idea quickly fading from future to past tense, relegating work in this area to the graveyard of failed technologies? The recently introduced Compute Express Link (CXL) may offer a path forward, with its persistent memory profile offering a universal PMem attachment point. Yet new technologies for memory-speed persistence seem years off, and may never become competitive with evolving DRAM and flash speeds. Without persistent memory itself, is future PMem research doomed? We offer two arguments for why reports of the death of PMem research are greatly exaggerated. First, the bulk of persistent-memory research has not in fact addressed memory persistence, but rather in-memory crash consistency, which was never an issue in prior systems where CPUs could not observe post-crash memory states. CXL memory pooling allows multiple hosts to share a single memory, all in different failure domains, raising crash-consistency issues even with volatile memory. Second, we believe CXL necessitates a "disaggregation" of PMem research. Most work to date assumed a single technology and set of features, i.e., speed, byte addressability, and CPU load/store access. With an open interface allowing new topologies and diverse PMem technologies, we argue for the need to examine these features individually and in combination. While one form of PMem may have been canceled, we argue that the research problems it raised not only remain relevant but have expanded in a CXL-based future.
- 23 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 23-30
Open AccessPersistent Memory Research in the Post-Optane Era
After over a decade of researcher anticipation for the arrival of persistent memory (PMem), the first shipments of 3D XPoint-based Intel Optane Memory in 2019 were quickly followed by its cancellation in 2022. Was this another case of an idea quickly fading from future to past tense, relegating work in this area to the graveyard of failed technologies? The recently introduced Compute Express Link (CXL) may offer a path forward, with its persistent memory profile offering a universal PMem attachment point. Yet new technologies for memory-speed persistence seem years off, and may never become competitive with evolving DRAM and flash speeds. Without persistent memory itself, is future PMem research doomed? We offer two arguments for why reports of the death of PMem research are greatly exaggerated. First, the bulk of persistent-memory research has not in fact addressed memory persistence, but rather in-memory crash consistency, which was never an issue in prior systems where CPUs could not observe post-crash memory states. CXL memory pooling allows multiple hosts to share a single memory, all in different failure domains, raising crash-consistency issues even with volatile memory. Second, we believe CXL necessitates a "disaggregation" of PMem research. Most work to date assumed a single technology and set of features, i.e., speed, byte addressability, and CPU load/store access. With an open interface allowing new topologies and diverse PMem technologies, we argue for the need to examine these features individually and in combination. While one form of PMem may have been canceled, we argue that the research problems it raised not only remain relevant but have expanded in a CXL-based future.
- Open Access
ISTRBoost: Importance Sampling Transfer Regression using Boosting
Current Instance Transfer Learning (ITL) methodologies use domain adaptation and sub-space transformation to achieve successful transfer learning. However, these methodologies, in their processes, sometimes overfit on the target dataset or suffer from negative transfer if the test dataset has a high variance. Boosting methodologies have been shown to reduce the risk of overfitting by iteratively re-weighing instances with high-residual. However, this balance is usually achieved with parameter optimization, as well as reducing the skewness in weights produced due to the size of the source dataset. While the former can be achieved, the latter is more challenging and can lead to negative transfer. We introduce a simpler and more robust fix to this problem by building upon the popular boosting ITL regression methodology, two-stage TrAdaBoost.R2. Our methodology,~\us{}, is a boosting and random-forest based ensemble methodology that utilizes importance sampling to reduce the skewness due to the source dataset. We show that~\us{}~performs better than competitive transfer learning methodologies $63\%$ of the time. It also displays consistency in its performance over diverse datasets with varying complexities, as opposed to the sporadic results observed for other transfer learning methodologies.Open AccessISTRBoost: Importance Sampling Transfer Regression using Boosting
Current Instance Transfer Learning (ITL) methodologies use domain adaptation and sub-space transformation to achieve successful transfer learning. However, these methodologies, in their processes, sometimes overfit on the target dataset or suffer from negative transfer if the test dataset has a high variance. Boosting methodologies have been shown to reduce the risk of overfitting by iteratively re-weighing instances with high-residual. However, this balance is usually achieved with parameter optimization, as well as reducing the skewness in weights produced due to the size of the source dataset. While the former can be achieved, the latter is more challenging and can lead to negative transfer. We introduce a simpler and more robust fix to this problem by building upon the popular boosting ITL regression methodology, two-stage TrAdaBoost.R2. Our methodology,~\us{}, is a boosting and random-forest based ensemble methodology that utilizes importance sampling to reduce the skewness due to the source dataset. We show that~\us{}~performs better than competitive transfer learning methodologies $63\%$ of the time. It also displays consistency in its performance over diverse datasets with varying complexities, as opposed to the sporadic results observed for other transfer learning methodologies. - 12 January 2020
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 54 (4) , 2152-2162
Incorporating Low-Cost Sensor Measurements into High-Resolution PM2.5 Modeling at a Large Spatial Scale
Low-cost air quality sensors are promising supplements to regulatory monitors for PM2.5 exposure assessment. However, little has been done to incorporate the low-cost sensor measurements in large-scale PM2.5 exposure modeling. We conducted spatially varying calibration and developed a down-weighting strategy to optimize the use of low-cost sensor data in PM2.5 estimation. In California, PurpleAir low-cost sensors were paired with Air Quality System (AQS) regulatory stations and calibration of the sensors was performed by Geographically Weighted Regression. The calibrated PurpleAir measurements were then given lower weights according to their residual errors and fused with AQS measurements into a Random Forest model to generate 1-km daily PM2.5 estimates. The calibration reduced PurpleAir’s systematic bias to ~0 μg/m³ and residual errors by 36%. Increased sensor bias was found to be associated with higher temperature and humidity as well as a longer operating time. The weighted prediction model outperformed the AQS-based prediction model with an improved random CV R2 of 0.86, an improved spatial CV R2 of 0.81, and a lower prediction error. The temporal CV R2 did not improve due to the temporal discontinuity of PurpleAir. The inclusion of PurpleAir data allowed the predictions to better reflect PM2.5 spatial details and hotspots.
- 12 January 2020
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 54 (4) , 2152-2162
Incorporating Low-Cost Sensor Measurements into High-Resolution PM2.5 Modeling at a Large Spatial Scale
Low-cost air quality sensors are promising supplements to regulatory monitors for PM2.5 exposure assessment. However, little has been done to incorporate the low-cost sensor measurements in large-scale PM2.5 exposure modeling. We conducted spatially varying calibration and developed a down-weighting strategy to optimize the use of low-cost sensor data in PM2.5 estimation. In California, PurpleAir low-cost sensors were paired with Air Quality System (AQS) regulatory stations and calibration of the sensors was performed by Geographically Weighted Regression. The calibrated PurpleAir measurements were then given lower weights according to their residual errors and fused with AQS measurements into a Random Forest model to generate 1-km daily PM2.5 estimates. The calibration reduced PurpleAir’s systematic bias to ~0 μg/m³ and residual errors by 36%. Increased sensor bias was found to be associated with higher temperature and humidity as well as a longer operating time. The weighted prediction model outperformed the AQS-based prediction model with an improved random CV R2 of 0.86, an improved spatial CV R2 of 0.81, and a lower prediction error. The temporal CV R2 did not improve due to the temporal discontinuity of PurpleAir. The inclusion of PurpleAir data allowed the predictions to better reflect PM2.5 spatial details and hotspots.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 175-182
Autonomic Partitioning for the Smart Control of Wireless Mesh Networks
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 175-182
Autonomic Partitioning for the Smart Control of Wireless Mesh Networks