Log inSign up
Brandon Amos
4,612 posts
user avatar
Brandon Amos
@brandondamos
🧙 RL @Reflection_AI past: @MetaAi @GoogleDeepmind @SCSatCMU @Cornell_Tech
New York, NY
bamos.github.io
Joined January 2014
2,431
Following
21.6K
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Brandon Amos
    @brandondamos
    Dec 8, 2025
    An update: I have left Meta Superintelligence Labs and joined @reflection_ai in NYC!! Today is my first day. I started in the Fundamental AI Research (FAIR) lab at Meta, then Facebook, over six (!) years ago as my first job out of the PhD. They were some formative years. The
    97K
  • user avatar
    Brandon Amos
    @brandondamos
    Feb 23, 2022
    Many standard probability distributions can be obtained by solving a maximum-entropy optimization problem over distributions. For example, the Gaussian maximizes the entropy subject to mean and covariance constraints. Jax source code: github.com/facebookresear… More resources: 🧵
    GIF
  • user avatar
    Brandon Amos
    @brandondamos
    Feb 2, 2022
    I just posted a new tutorial on amortized optimization! It covers foundations for learning to optimize and how they are key ingredients for VAEs, RL, meta-learning, and sparse coding with budding applications in DEQs, convex optimization, and beyond arxiv.org/abs/2202.00665 🧵
  • user avatar
    Brandon Amos
    @brandondamos
    Sep 4, 2024
    📢 Today's my first day at Cornell Tech :) I will continue my full-time position as a scientist at Meta, and am teaching ML here on the side for the semester with @volokuleshov. The course is open source and you can follow everything in this repo: github.com/kuleshov/corne…
    69K
  • user avatar
    Brandon Amos
    @brandondamos
    Jul 20, 2023
    📚 My mini-book on amortized optimization is officially published! Via the Foundations and Trends® in Machine Learning journal (nowpublishers.com/MAL) Buy a physical copy: a.co/d/4IlD3oo Free online version: arxiv.org/abs/2202.00665 Source code: github.com/facebookresear…
    72K
  • user avatar
    Brandon Amos
    @brandondamos
    Jun 22, 2022
    I just open-sourced 200+ slides from the major presentations I've given over the past 5 years: github.com/bamos/presenta…
    GIF
  • user avatar
    Brandon Amos
    @brandondamos
    Apr 15, 2021
    We've released differentiable convex optimization layers for JAX! Code: github.com/cvxgrp/cvxpyla… Tutorial: nbviewer.jupyter.org/github/cvxgrp/… NeurIPS paper: arxiv.org/abs/1910.12430 Blog post: locuslab.github.io/2019-10-28-cvx… With @akshaykagrawal, @ShaneBarratt, S. Boyd, S. Diamond, and @zicokolter
  • user avatar
    Brandon Amos
    @brandondamos
    Oct 8, 2024
    📢 My team at Meta is hiring PhD research interns! We study core machine learning, optimization, amortization, flows, and control for modeling and interacting with complex systems (...and we use basic physics... 🙃) Please apply here and message me: metacareers.com/jobs/532549086… 🧵
    93K
  • user avatar
    Brandon Amos
    @brandondamos
    May 2, 2019
    A life update. I've dodged all of the attacks and have successfully defended my PhD thesis. Thanks everybody! My thesis document and slides are available on GitHub
    GitHub - bamos/thesis: Differentiable Optimization-Based Modeling for Machine Learning
    From github.com
  • user avatar
    Brandon Amos
    @brandondamos
    Mar 18, 2019
    Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly K. Kandasamy et al. Python Library: github.com/dragonfly/drag… Docs: dragonfly-opt.readthedocs.io/en/master/
  • user avatar
    Brandon Amos
    @brandondamos
    Jul 19, 2024
    :) (context for the reader: this is a slide from my fundamental differentiable optimization layers talk, which I've been giving since ~2017. @alfcnz has been inspirational on the "soft-argmax" naming for years!!)
    user avatar
    Alex Shtoff
    @AlexShtf
    Jul 18, 2024
    I am the only one on #ML twitter who doesn't like the name 'softmax' for exp(x) / sum(exp(x)) , and instead prefers the name 'soft-argmax'? Softmax is LogSumExp!
    58K
  • user avatar
    Brandon Amos
    @brandondamos
    Jun 13, 2022
    Our new paper on Meta Optimal Transport uses amortized optimization to predict initializations and improve optimal transport solver runtimes by 100x and more. With @CohenSamuel13 @GiuliaLuise1 @IevgenRedko Paper: arxiv.org/abs/2206.05262 JAX source code: github.com/facebookresear…
    00:00
  • user avatar
    Brandon Amos
    @brandondamos
    Jul 18, 2024
    📢 In our new @UncertaintyInAI paper, we do neural optimal transport with costs defined by a Lagrangian (e.g., for physical knowledge, constraints, and geodesics) Paper: arxiv.org/abs/2406.00288 JAX Code: github.com/facebookresear… (w/ A. Pooladian, C. Domingo-Enrich, @RickyTQChen)
    GIF
    43K
  • user avatar
    Brandon Amos
    @brandondamos
    Nov 11, 2024
    Flows and transport methods are widely used to connect one distribution to another. What about going up one level to transporting between distributions over distributions? My new talk overviews some methods in this space: bamos.github.io/presentations/… & a quick 🧵 below
    GIF
    30K