Richard Wu

Canada Contact Info
1K followers 500+ connections

Join to view profile

About

Building the financial rails for the next trillion dollar asset class: NFTs.

Activity

Join now to see all activity

Experience & Education

  • Tensor

View Richard’s full experience

See their title, tenure and more.

or

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Publications

  • Attention-based Learning for Missing Data Imputation in HoloClean

    MLSys 2020

    We study the problem of missing data imputation, a data validation task that machine learning researchers and practitioners confront regularly. We focus on mixed (discrete and continuous) data and introduce AimNet, an attention-based learning network for missing data imputation. AimNet utilizes a variation of the dot product attention mechanism to learn interpretable, structural properties of the mixed data distribution and relies on the learned structure to perform imputation. We perform an…

    We study the problem of missing data imputation, a data validation task that machine learning researchers and practitioners confront regularly. We focus on mixed (discrete and continuous) data and introduce AimNet, an attention-based learning network for missing data imputation. AimNet utilizes a variation of the dot product attention mechanism to learn interpretable, structural properties of the mixed data distribution and relies on the learned structure to perform imputation. We perform an extensive experimental study over 14 real-world data sets to understand the role of attention and structure on data imputation. We find that the simple attention-based architecture of AimNet outperforms state-of-the-art baselines, such as ensemble tree models and deep learning architectures (e.g., generative adversarial networks), by up to 43% in accuracy on discrete values and up to 26.7% in normalized-RMS error on continuous values. A key finding of our study is that, by learning the structure of the underlying distribution, the attention mechanism can generalize better on systematically-missing data where imputation requires reasoning about functional relationships between attributes.

    See publication

  • Evaluation of NUMA-Aware Scheduling in Warehouse-Scale Clusters

    IEEE CLOUD 2019

    Non-uniform memory access (NUMA) has been extensively studied at the machine level but few studies have examined NUMA optimizations at the cluster level. This paper introduces a holistic NUMA-aware scheduling policy that combines both machine-level and cluster-level NUMA-aware optimizations. We evaluate our holistic NUMA-aware scheduling policy on Google’s production cluster trace with a cluster scheduling simulator that measures the impact of NUMA-aware scheduling under two scheduling…

    Non-uniform memory access (NUMA) has been extensively studied at the machine level but few studies have examined NUMA optimizations at the cluster level. This paper introduces a holistic NUMA-aware scheduling policy that combines both machine-level and cluster-level NUMA-aware optimizations. We evaluate our holistic NUMA-aware scheduling policy on Google’s production cluster trace with a cluster scheduling simulator that measures the impact of NUMA-aware scheduling under two scheduling algorithms, Best Fit and Enhanced PVM (E-PVM). While our results highlight that a holistic NUMA-aware scheduling policy substantially increases the proportion of NUMA-fit tasks by 22.0% and 25.6% for both the Best Fit and E-PVM scheduling algorithms, respectively, there is a non-trivial tradeoff between cluster job packing efficiency and NUMA-fitness for the E-PVM algorithm under certain circumstances.

    See publication

  • Unravelling the Quasi-Periodic Dynamics of Global Influenza Outbreaks

    The Data Open 2018-2019 Championships

    See publication

  • SQL Joins with Interleaved Tables: A Natural Extension of NewSQL Databases

    See publication

  • The Solution to America's Education Crisis

    The Data Open 2017 Championships

    See publication

Honors & Awards

  • First Place @ the University of Toronto Citadel Data Open Datathon 2018

    Correlation One and Citadel

    Competed at the University of Toronto Citadel Data Open datathon in a team of 4 and placed first out of 25 teams, receiving a $20,000 cash prize.

    One of the finalist teams that competed in the 2018-2019 Data Open Championships.

    https://uwaterloo.ca/computer-science/news/waterloo-students-win-20000-citadel-and-citadel-securities

  • K.C. Lee Computer Science Scholarship

    University of Waterloo

    Scholarship selection is based on excellent academic standing and commitment to Computer Science as evidenced by related work experience and/or related special projects.

  • Konrad Group Digital Technology Scholarship

    Konrad Group and University of Waterloo

    Scholarship selection is made on the basis of academic achievement and a demonstrated interest in pursuing a career in digital technology (i.e., work-term experiences, extracurricular activities, and/or project work).

  • First Place @ the University of Waterloo Citadel Data Open Datathon 2017

    Correlation One and Citadel

    Competed at the University of Waterloo Citadel Data Open datathon in a team of 4 and placed first out of 20 teams, receiving a $20,000 cash prize.

    One of top 20 finalist teams that competed in 2017 Data Open Championships at the NYSE.

    https://uwaterloo.ca/statistics-and-actuarial-science/news/first-annual-datathon-university-waterloo

  • Joe C. Lee Math Entrepreneurial Scholarship

    University of Waterloo

    Scholarship selection is based on scholastic excellence (minimum 80% average), a demonstrated passion for entrepreneurship, involvement in the community, and related extracurricular activities, e.g., completion of side business projects, participation in competitions, etc.

  • Hack the North 2015 champions

    Hack the North

    Hack the North is Canada’s premier hackathon, where 1,000 students of different skill levels come together from across the world to experiment and create unique software or hardware projects from scratch.

  • Software Engineering Entrance Scholarship

    University of Waterloo

    Scholarship selection is based on academic performance and extracurriculars. Awarded to several incoming Software Engineering students.

  • President's Scholarship of Distinction

    University of Waterloo

    Awarded to incoming University of Waterloo student's with a 95% or higher admissions average.

More activity by Richard

View Richard’s full profile

  • See who you know in common
  • Get introduced
  • Contact Richard directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Richard Wu in Canada

66 others named Richard Wu in Canada are on LinkedIn

See others named Richard Wu

Add new skills with these courses

See all courses