Assistant prof @CIS_Penn. Machine learning for systems, databases.
- Tweets 673
- Following 1,084
- Followers 1,684
- Likes 3,129
ALT A four-step cycle diagram showing feedback between database users and engineers. โ User submits their workload to the system: A square grid of colored squares represents the workload (3 green, 2 purple). โก Engineers observe properties of the workload: A database cylinder leads to a chart showing workload composition: purple 30%, green 60%. A speech bubble from an engineer character says, โMost queries are green. Iโll trade lower purple performance for higher green performance.โ โข Engineers identify hotspots and optimize their system. โฃ Users optimize their workloads based on their platform: A speech bubble from a user character says, โOur platform is good at green, but bad at purple โ send more green!โ An arrow shows users adjusting the workload and feeding it back into the system. Overall, the diagram illustrates a feedback loop where system optimizations influence user behavior, which then shapes the workload engineers observe.
ALT Infographic describing LimeQO, a workload-level, offline, learned query optimizer. On the left, it shows a workload consisting of multiple queries (qโ to qโ), each with a default execution time (3s, 9s, 12s, 22s respectively). On the right, alternate plans (hโ, hโ, hโ) show varying execution times for each query, with some entries missing (represented by question marks). For example, qโ takes 1s under hโ, much faster than the 3s default. A specific callout highlights that for qโ, plan hโ reduced the time from 12s to 3s, but took 18s to find, resulting in a benefit of 9s gained / 18s search. The image poses the question: โWhere should we explore next to maximize benefit?โ The image credits Zixuan Yi et al., SIGMOD '25, and provides a link: https://rm.cab/limeqo
ALT Infographic describing BayesQO, an offline, multi-iteration learned query optimizer. On the left, it shows a Variational Autoencoder (VAE) being pretrained to reconstruct query plans from vectors, using orange-colored plan diagrams. The decoder part of the VAE is retained. In the center and right, the image shows Bayesian optimization being performed in the learned vector space: new vectors are decoded into query plans, tested for latency, and refined iteratively. At the bottom, a library of optimized query plans is used to train a robot labeled โLLM,โ which can then generate new plans directly. The caption reads: "We get a fast query, but also a library of high-quality plans. We can train an LLM to speed up the process for next time!" The image credits Jeff Tao et al., SIGMOD '25, and links to https://rm.cab/bayesqo.
ALT A workload matrix. Each row represents a query, and each column represents a hint. Each entry is the latency of that query using that hint. Some values are unobserved, others are observed.
ALT The LimeQO system model. A workload matrix is continuously approximated. Then, offline exploration is used to verify which query plans represent improvements.
ALT A plot of P90 tail latency for PostgreSQL major versions 8 through 16. Tail latency is cut approximately in half from version 8 to version 16.
ALT The three pillars of machine programming: invention, adaption, and intention. Inventive and adaptive systems are called "instance optimized" systems. Inventive and intentional systems are "program synthesis." Adaptive and intentional systems are "auto tuning."
ALT A list of the six papers described below. AdaChain is presented in session H4 on Wednesday at 1:30pm in Orca AutoSteer is presented in session A4 on Wednesday at 1:30pm in Grand Ballroom Robust Cardinality is presented in session C5 at 3:30pm in Ballroom AB QO-Insight is presented in demo group B on Tuesday at 3:30pm Superoptimization is presented at AIDB on Friday at 2:30pm RLShard is presented at AIDB on Friday at 2:45pm
