M
Michael Schaarschmidt
Researcher at University of Cambridge
Publications - 19
Citations - 320
Michael Schaarschmidt is an academic researcher from University of Cambridge. The author has contributed to research in topics: Reinforcement learning & Deep learning. The author has an hindex of 9, co-authored 15 publications receiving 228 citations.
Papers
More filters
Proceedings ArticleDOI
BOAT: Building Auto-Tuners with Structured Bayesian Optimization
TL;DR: BOAT is presented, a framework which allows developers to build efficient bespoke auto-tuners for their system, in situations where generic auto- Tuners fail, and is a novel extension of the Bayesian optimization algorithm.
Posted Content
LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations
TL;DR: Results show LIFT controllers initialized from demonstrations can outperform human baselines and heuristics across latency metrics and space usage by up to 70% and are demonstrated in two case studies in database compound indexing and resource management in stream processing.
Proceedings ArticleDOI
Reinforcement Learning for the Adaptive Scheduling of Educational Activities
Jonathan Bassen,Bharathan Balaji,Michael Schaarschmidt,Candace Thille,Jay Painter,Dawn Zimmaro,Alex Games,Ethan Fast,John C. Mitchell +8 more
TL;DR: This paper demonstrates the first RL model to schedule educational activities in real time for a large online course through active learning, and produces similar learning gains to a self-directed condition using fewer educational activities and with lower dropout rates.
Proceedings ArticleDOI
Pre-training via Denoising for Molecular Property Prediction
Sheheryar Zaidi,Michael Schaarschmidt,James Martens,Hyunjik Kim,Yee Whye Teh,A. Sánchez-González,Peter W. Battaglia,R.P. Pascanu,Jonathan Godwin +8 more
TL;DR: A pre-training technique based on denoising that achieves a new state-of-the-art in molecular property prediction by utilizing large datasets of 3D molecular structures at equilibrium to learn meaningful representations for downstream tasks is described.
Journal ArticleDOI
Quaestor: query web caching for database-as-a-service providers
TL;DR: The main idea is to enable application-independent caching of query results and records with tunable consistency guarantees, in particular bounded staleness to enable data-centric cloud services to trade latency against staleness bounds, e.g. in a database-as-a-service.