AI People Wiki

Builders & open source

Lorenzo Stella

Computer scientist, Amazon

Lorenzo Stella is a computer scientist at Amazon Web Services who works on time series forecasting and optimization software. Stella is the second author of the Chronos paper (2024), which introduced Amazon's pretrained time series forecasting models, a co-author of Chronos-2 (2025), and a co-author of GluonTS, a Python toolkit for probabilistic time series modeling. Stella's earlier research covered algorithms for large-scale nonsmooth optimization.12345

At a glance

Current role
Computer scientist
Company
Amazon
Sector
Company
Work listed
3
Sources cited
7
Profile reviewed

Career

Stella works as a computer scientist at AWS, which Stella's GitHub profile also lists as the current organization. Stella's earlier research addressed algorithms for large-scale nonsmooth optimization problems, their theoretical analysis and their efficient implementation.12

Research and software

Stella's optimization research includes papers on forward-backward quasi-Newton methods (2017), Douglas-Rachford splitting and ADMM for nonconvex problems (2022) and adaptive proximal algorithms (2024), and the Julia packages ProximalAlgorithms.jl and ProximalOperators.jl.56

In time series forecasting, Stella co-authored Deep State Space Models (NeurIPS 2018), the GluonTS toolkit paper (JMLR 2020), Chronos (2024), the fev-bench benchmark (2025) and Chronos-2 (2025).5347

Work and contributions

  • Chronos Open weights

    Second author of "Chronos: Learning the Language of Time Series" (2024); Stella's site lists Chronos among Stella's projects.36

  • Chronos-2 Open weights

    Co-author of "Chronos-2: From Univariate to Universal Forecasting" (2025).45

  • GluonTS Open-source code

    Co-author of the 2020 JMLR paper on GluonTS, a Python toolkit for probabilistic time series modeling with a focus on deep learning architectures.56

Timeline

  1. Co-authored a paper on complexity estimates and accelerated variants of Douglas-Rachford splitting at IEEE CDC.5
  2. Co-authored Deep State Space Models for Time Series Forecasting at NeurIPS 2018.5
  3. Co-authored the GluonTS paper on probabilistic and neural time series modeling in Python.5
  4. Posted the Chronos paper on pretrained time series models as second author.3
  5. Co-authored fev-bench, a benchmark for time series forecasting.7
  6. Co-authored the Chronos-2 paper on universal forecasting.4

Where they work

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

7 sources · profile reviewed Oct 22, 2026 · data updated Oct 22, 2026

  1. Lorenzo Stella — homepageLorenzo Stella · Official page · accessed Oct 22, 2026
  2. lostella (Lorenzo Stella) on GitHubGitHub · Official page · accessed Oct 22, 2026
  3. Chronos: Learning the Language of Time Series (arXiv 2403.07815)arXiv · Paper · published Mar 12, 2024 · accessed Oct 22, 2026
  4. Chronos-2: From Univariate to Universal Forecasting (arXiv 2510.15821)arXiv · Paper · published Oct 17, 2025 · accessed Oct 22, 2026
  5. Lorenzo Stella — Research (selected publications)Lorenzo Stella · Official page · accessed Oct 22, 2026
  6. Lorenzo Stella — ProjectsLorenzo Stella · Official page · accessed Oct 22, 2026
  7. fev-bench: A Realistic Benchmark for Time Series Forecasting (arXiv 2509.26468)arXiv · Paper · published Sep 30, 2025 · accessed Oct 22, 2026