-
π» Computational scientist
@ Argonne National Laboratory (ALCF) -
π§ͺ Interested in:
-
π If youβre curious
-
π How I got here
My current research focuses on using deep generative modeling to help build better sampling algorithms in lattice gauge theory. In particular, Iβm interested in building gauge equivariant neural network architectures and using inductive priors to incorporate physical symmetries into machine learning models.
I received my PhD in Physics from the University of Iowa in 2019 and my thesis was on Learning Better Physics: A Machine Learning Approach to Lattice Gauge Theory.
Prior to this, I completed two bachelors degrees (Engineering Physics and Applied Mathematics, 2015) at The University of Illinois at Urbana-Champaign. My undergraduate dissertation was titled Energy Storage in Quantum Resonators and was supervised by Professor Alfred HΓΌbler within the Center for Complex Systems Research at UIUC4.
[NOTE]: You can find a full list of my publications on my Google Scholar.
-
Intro to HPC Bootcamp: Engaging New Communities Through Energy Justice Projects
Journal of Computational Science, 2024 -
Thorough Characterization and Analysis of Large Transformer Model Training At-Scale
Proc. ACM Meas. Anal. Comput. Syst. 03/2024 -
MLMC: Machine Learning Monte Carlo for Lattice Gauge Theory
S. Foreman et al.Β Lattice, 2023 (Proceedings), 12/2023 -
Protein Generation via Genome-scale Language Models with Bio-physical Scoring
@ SCβ23, 11/2023 -
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery [β¦]
@ NeurIPS 2023 AI For Science Workshop, 10/2023 -
Comprehensive Performance Study of LLMs on Novel AI Accelerators
M. Emani, S. Foreman, et al., IPDPS 2024, 10/2023 -
Exploratory Analysis of Climate Data with
ClimRR
S. Foreman, Intro to HPC Bootcamp @ NERSC, 08/2023 -
π GenSLMs: Genome-scale language models reveal SARS-Cov-2 evolutionary dynamics
@ SCβ22 10/2022 -
Lattice QCD and Particle Physics
A.S. Kronfeld et al., 07/2022 -
Applications of ML to Lattice QFT
D. Boyda, S. CalΓ, S. Foreman, et al., [arXiv:2202.05838], 02/2022 -
LeapFrogLayers: Trainable Framework for Effective Sampling
S. Foreman, X.Y. Jin, J.C. Osborn, Lattice, 2021 -
HMC with Normalizing Flows [slides]
S. Foreman et al., Lattice, 2021 -
Deep Learning Hamiltonian Monte Carlo [+ poster]
S. Foreman, X.Y. Jin, & J.C. Osborn, @ SimDL Workshop @ ICLR, 2021 -
Machine Learning and Neural Networks for Field Theory
S. Foreman, X.Y. Jin, & J.C. Osborn, SnowMass, 2020 -
Examples of renormalization group transformations for image sets
S. Foreman et al., Physical Review E., 2018 -
RG inspired Machine Learning for lattice field theory
S. Foreman et al., arXiv:1710.02079, 2017 -
Large Energy Density in Three-Plate Nanocapacitors due to Coulomb Blockade
S. Foreman et al., J. Appl. Phys, 2018
[!TIP]
AuroraGPT @ HPC User Forum, 2024 [09/2024]
<iframe class="slide-deck" loading="lazy" allow="picture-in-picture" src="https://samforeman.me/talks/hpc-user-forum/slides" title="AuroraGPT" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style="aspect-ratio: 1.5;"> </iframe>
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://samforeman.me/talks/llms-at-scale/slides" title="Training LLMs at Scale" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>Training LLMs at Scale @ ATPESC, 2024 [08/2024]
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://samforeman.me/talks/llms-on-polaris/slides" title="LLMs on Polaris" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/parallel-training-slides" title="Parallel Training Techniques" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
LLMs from Scratch @ LLM Tutorial Workshop [02/2024]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/llm-workshop-talk" title="LLMs from Scratch" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Creating Small(-ish) LLMs @ LLM Tutorial Workshop (1) [11/2023]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/LLM-tutorial" title="Creating Small(-ish) LLMs" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/oneapi-talk" title="Exascale Science on Aurora" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
LLM Lunch Talk @ ALCF Hands On HPC Workshop [10/2023]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/llm-lunch-talk/#/section" title="LLMs on Polaris" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/scaling4science/#/section" title="Scaling LLMs for Science and Ongoing Collaborations" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
MLMC: Machine Learning Monte Carlo @ Lattice 2023 [07/2023]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/lattice23/#/title-slide" title="MLMC: Machine Learning Monte Carlo" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Generative Modeling and Efficient Sampling @ PASC23 [07/2023]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/lqcd-pasc23/" title="Generative Modeling and Efficient Sampling" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Efficient Sampling for LGT @ Deep Fridays @ U. Bologna [04/2023]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/deep-fridays/" title="Efficient Sampling for LGT" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/ai4sci-large-scale-training/#" title="Large Scale Training" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Hyperparameter Management @ ALCF SDL Workshop [10/2022]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/hparam-management-sdl2022" title="Hyperparameter Management" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Statistical Learning @ ATPESC 2022 [08/2022]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/ATPESC-StatisticalLearning/#/" title="Statistical Learning" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Scientific Data Science: An Emerging Symbiosis @ ANL (05/2022)
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/anl-job-talk" title="Scientific Data Science" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Machine Learning in HEP @ UNC Greensboro [03/2022]
- Machine Learning in HEP, at UNC Greensboro, March 2022
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/physicsSeminar" title="Machine Learning in HEP" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style="width:100%!important; border:none;border-radius:0.25rem;"> </iframe>
[!TIP]
Accelerated Sampling Methods for LGT, @ DWQ @ 25 [BNL] [12/2021]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/l2hmc-dwq25/" title="Accelerated Sampling Methods for LGT" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://saforem2.github.io/l2hmc_talk_ect2021" title="Training Topological Samplers for LGT" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
l2hmc-qcd @ MIT Lattice Group Seminar [2021]
l2hmc-qcd at the MIT Lattice Group Seminar, 2021
[!TIP]
<iframe loading="lazy" allow="picture-in-picture" src="https://slides.com/samforeman/dlhmc/embed" title="Deep Learning HMC for Improved Gauge Generation" scrolling="no" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
Machine Learning for Lattice QCD @ U. Iowa [2020]
<iframe loading="lazy" allow="picture-in-picture" src="https://slides.com/samforeman/l2hmc-qcd/embed" title="Machine Learning for Lattice QCD" align="center" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen> </iframe>
[!TIP]
[!TIP]
π
saforem2/
-
Organizer for:
-
SC24 Workshop: High Performance Python for Science at Scale (HPPSS), November 2024
-
SC23 Workshop: High Performance Python for Science at Scale (HPPSS), November 2023
-
Machine Learning and Quantum Computing for Earth Sciences at 17th U. S. National Congress on Computational Mechanics, July 2023
-
TableΒ 1: π Experience
Position | @ | Start | End |
---|---|---|---|
Assistant Computational Scientist | ALCF | 2022 | β |
Postdoc | ALCF | 2019 | 2022 |
Graduate Researcher | ANL | 2018 | 2019 |
TableΒ 2: π Education
Degree | In | @ | End |
---|---|---|---|
PhD | Physics | University of Iowa | 2019 |
B.Sc | Physics | UIUC | 2015 |
B.Sc | Math | UIUC | 2015 |
[!TIP]
<script> /** Developed by Prashant Shrestha + https://prashant.me */ var lastfmData = { baseURL: "https://ws.audioscrobbler.com/2.0/?method=user.getrecenttracks&user=", // Your Last.fm Username user: "saforem2", // Your API key api_key: "1dbc15037c1fe71ce06acbb3f73adc75", additional: "&format=json&limit=1" }; var getSetLastFM = function() { $.ajax({ type: "GET", url: lastfmData.baseURL + lastfmData.user + "&api_key=" + lastfmData.api_key + lastfmData.additional, dataType: "json", success: function(resp) { var recentTrack = resp.recenttracks.track[0]; var formatted = "" + recentTrack.name; $("a#tracktitle") .html(formatted) .attr("href", recentTrack.url) .attr("title", recentTrack.name + " by " + recentTrack.artist["#text"]) .attr("target", "_blank"); var artistFormatted = "" + recentTrack.artist["#text"]; $("a#trackartist") .html(artistFormatted) .attr("title", "Artist : " + recentTrack.artist["#text"]); $("img#trackart").attr("src", recentTrack.image[2]["#text"]); }, error: function(resp) { $("a#tracktitle").html( "" + "Silence!" ); $("img#trackart").attr("src", "π§π»βπ»"); var artistFormatted = "Sam Foreman"; $("a#trackartist") .html(artistFormatted) .attr("href", "https://samforeman.me"); } }); }; // Get the new one. getSetLastFM(); // Start the countdown. setInterval(getSetLastFM, 10 * 100); </script>
Tip
highlight yellow
highlight pink
highlight green
highlight-blue
circle sketch highlight
import datetime
from rich import print
now = datetime.datetime.now()
day = now.strftime("%Y-%m-%d")
time = now.strftime("%H:%M:%S")
print(' '.join([
"[#838383]Last Updated[/]:",
f"[#E599F7]{day}[/]",
"[#838383]@[/]",
f"[#00CCFF]{time}[/]"
]))
Last Updated: 2024-10-08 @ 18:17:16
Footnotes
-
So far, for: {Lattice QCD, Quantum Mechanics, Biology (Protein Generation, Drug Discovery), and Climate Modeling / Weather Forecasting} β©
-
Mostly trying to get supercomputers to stop yelling at each other π« β©
-
If this sounds like something youβd be interested in doing, please feel free to reach out to me! β©