19 open source projects by stanford-futuredata

DAWNBench: An End-to-End Deep Learning Benchmark and Competition

ASAP: Prioritizing Attention via Time Series Smoothing

ColBERT: Contextualized Late Interaction over BERT (SIGIR'20 paper)

Simple baselines for "Learned Indexes"

End-to-end earthquake detection pipeline via efficient time series similarity search

Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.org/abs/1901.11399

2AD analysis prototype and logs from sample applications

MacroBase: A Search Engine for Fast Data

Sparser: Raw Filtering for Faster Analytics over Raw Data

Accelerating network inference over video

Sketching linear classifiers over data streams with the Weight-Median Sketch (SIGMOD 2018).

No description, website, or topics provided.

Simplified Moment Sketch Implemntation

Code for "Heterogenity-Aware Cluster Scheduling Policies for Deep Learning Workloads", which appeared at OSDI 2020

Code for "Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP", which appeared at SOSP 2021

No description, website, or topics provided.

No description, website, or topics provided.

Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.

Willump Is a Low-Latency Useful Machine learning Platform.