Matei Zaharia
where else to find them
what they talk about
all 16 in the filters
where they keep going back
- Scale By the Bay2 editions2017–2020
all 14 in the filters
on a stage with
all 36 in the filters
who talks about the same things
- Reynold Xin15 talks
- Frank Munz8 talks
- Andy Petrella14 talks
- Dean Wampler29 talks
- Denny Lee10 talks
- Holden Karau39 talks
| title | conference | date |
|---|---|---|
| Programming Large Language Models with Algebraic Effect Handlers and the Selection Monad | LMPL 2025 | 2025-10-12 |
Pangolin models LLM calls as algebraic effects and uses a selection monad to search and score nondeterministic outputs; handlers expose a multi‑shot… | ||
| Compass: Encrypted Semantic Search with High Accuracy | OSDI '25 | 2025-07-07 |
Compass implements encrypted semantic search by running HNSW-style graph traversal on encrypted embeddings with a client-side retriever and ORAM-backed… | ||
| Keynote Day 2 - Full | Data + AI Summit 2024 | 2024-06-10 |
Announces include Uniform GA with 4+ exabytes loaded and Delta processing cited at ~9 exabytes, plus a 73% BI performance uplift over two years; DuckDB adds… | ||
| Evolving Data Governance With Unity Catalog | Data + AI Summit 2024 | 2024-06-10 |
Announces an open-source Unity Catalog (v0.1) now public on GitHub and accepted by the Linux Foundation, ships table, volume (unstructured) and AI… | ||
| Announcing Databricks Clean Rooms with Live Demo | Data + AI Summit 2024 | 2024-06-10 |
Databricks launches a clean rooms product as Public Preview on AWS + Azure that runs arbitrary computations including Python ML code and notebooks not just… | ||
| Data Sharing and Cross-Organization Collaboration | Data + AI Summit 2024 | 2024-06-10 |
An open protocol called Delta Sharing serves Parquet files so organizations can publish parts of tables directly to pandas, Apache Spark, Tableau, Power BI or… | ||
| Open Sourcing Unity Catalog Live Onstage | Data + AI Summit 2024 | 2024-06-10 |
Unity Catalog becomes an open source project live onstage: a GitHub repository is created, navigated to the settings, and toggled from private to public using… | ||
| Matei Zaharia, Databricks | Databricks Data + AI Summit 2023 | Databricks Data + AI Summit 2023 | 2023-06-26 |
Databricks announces concrete pieces: a Unity Catalog that enforces lineage and access across structured tables and unstructured files, Delta tables that… | ||
| Hamband: RDMA Replicated Data Types | PLDI 2022 | 2022-06-13 |
First hybrid replicated data types for RDMA that implement synchronization groups (strongly connected components of a conflict graph) with a single-leader… | ||
| Data-Parallel Actors: A Programming Model for Scalable Query Serving Systems | 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI '22) | 2022-04-04 |
Data-parallel actors (DPA) is a programming model and runtime (Uniserv) that composes single-node components into distributed query-serving systems using… | ||
| Data Mesh and Lakehouse | State of Data Mesh 2022 | 2022-02-23 |
Lakehouse systems implement warehouse features on open file formats using metadata layers (Delta Lake, Apache Hudi) that add ACID transactions, time travel… | ||
| Contracting Wide-area Network Topologies to Solve Flow Problems Quickly | NSDI ’21 | 2021-04-12 |
NCFlow contracts the WAN into clusters and replaces the full multi-commodity LP with a tiny aggregated inter-cluster flow plus parallel per-cluster… | ||
| Scaling Databricks to Run Data & AI Workloads on Millions of VMs | Scale By the Bay 2020 | 2020-11-12 |
Databricks runs millions of VMs across ~7,000 customers processing exabytes per day and builds a Scala control plane on Kubernetes with Envoy and Prometheus… | ||
| Offload Annotations: Bringing Heterogeneous Computing to Existing Libraries... | USENIX ATC '20 | 2020-07-15 |
Offload Annotations maps existing CPU libraries like NumPy, Pandas and scikit‑learn to GPU kernels (PyTorch, cuML) via small annotation files and a runtime… | ||
| POSH: A Data-Aware Shell | USENIX ATC '20 | 2020-07-15 |
POSH is a drop‑in shell that offloads I/O‑heavy pipeline stages to proxy servers colocated with NFS storage, using an annotation language to declare which… | ||
| From Laptop to Lambda: Outsourcing Everyday Jobs to Thousands of Transient Functional Containers | USENIX ATC '19 | 2019-07-10 |
A toolkit called gg packages programs as content‑hashed lightweight containers called gg thunks and composes them into a linked GG IR to offload entire jobs to… | ||
| Composable Parallel Processing in Apache Spark and Weld | Scale By the Bay 2017 | 2017-11-16 |
Explains how Apache Spark’s DataFrames and Datasets expose a schema-aware DSL and runtime (Spark SQL/Tungsten) that enables filter pushdown, runtime codegen… | ||
| Spark 2.0 | Scala Days Berlin 2016 | 2016-06-15 |
Overview of what changed and what actually works: Spark 2.0 tightens schemas with DataFrames and Datasets so the engine can optimize, uses a binary columnar… | ||
| New Directions for Spark in 2015 | Strata + Hadoop World San Jose 2015 | 2015-02-17 |
Spark claims dramatic performance and ecosystem gains in 2014 and concrete plans for 2015: contributor count grows from 150 to 500, codebase from 190k to 370k… | ||
| How Companies are Using Spark, and Where the Edge in Big Data Will Be | Strata Conference 2014 | 2014-02-11 |
Apache Spark (Apache/Berkeley) aims to push value from data by improving speed and algorithmic power on commodity Hadoop clusters. Claims include up to 100x… | ||
| nothing matches | ||