Pedro Bruel (@pedrobruel) 's Twitter Profile
Pedro Bruel

@pedrobruel

Research Scientist @HPE_labs.
Hardware/Software Codesign. Performance Modeling and Optimization. Linux, Emacs, and org-mode enthusiast @[email protected]

ID: 1123369224414560256

linkhttps://phrb.github.io calendar_today30-04-2019 23:31:09

26 Tweet

60 Followers

510 Following

Pedro Bruel (@pedrobruel) 's Twitter Profile Photo

Hey 🔎Julia Evans🔍, could I use pages 7 and 8 from your containers zine on an undergrad class on OS-level virtualization I'm making? Also, your zines are great!

Willie Neiswanger (@willieneis) 's Twitter Profile Photo

(1/9) Presenting: Bayesian Algorithm Execution (BAX) and the InfoBAX algorithm. Bayesian optimization finds global optima of expensive black-box functions. But what about other function properties? w/ @KAlexanderWang Stefano Ermon at #ICML2021 URL: willieneis.github.io/bax-website

Papers with Code (@paperswithcode) 's Twitter Profile Photo

🔥The ML Reproducibility Challenge is back! The 5th annual edition now expands to cover papers from 9 major ML conferences: NeurIPS, ICML, ICLR, ACL-IJCNLP, EMNLP, CVPR, ICCV, AAAI and IJCAI. Find more here: paperswithcode.com/rc2021

Onur Mutlu (@_onurmutlu_) 's Twitter Profile Photo

We cover: 1. high-performance prefetcher design using reinforcement learning 2. acceleration methods for widely-different machine learning models (used at Google), 3. support for better security & performance in DRAM, 4. fast true random number generation using modern DRAM

Pedro Bruel (@pedrobruel) 's Twitter Profile Photo

Extensive replication project in cancer biology; would be very interesting to do the same with performance tuning and other domains. I wonder whether more code and data would be available

Deyan Ginev (@dginev) 's Twitter Profile Photo

📢 Welcome to ar5iv.org Change the "X" in any arXiv article link to the "5" in ar5iv to get a modern HTML5 document. Thread: what is included, why now, and how we hope to merge back into arXiv. #OA #OpenScience #preprints 1/10

Jascha Sohl-Dickstein (@jaschasd) 's Twitter Profile Photo

Have you ever done a dense grid search over neural network hyperparameters? Like a *really dense* grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish colors to hyperparameters for which training diverges.