We are excited to announce a two-week seminar on singular learning theory (SLT) and AI alignment, taking place from June 19th to July 2nd in Berkeley. EDIT: The conference will have a two-part structure, June 19th-23rd virtual and June 24th-July 2nd in-person at Rose Garden Inn in Berkeley.
During this workshop, we'll bring together singular learning theorists and alignment researchers to connect and further the applications of singular learning theory to alignment. The workshop aims to familiarize alignment researchers with SLT, seed new research collaborations, and develop tools based on SLT ideas. There will be talks by Daniel Murfet, Susan Wei, Shaowei Lin, Alexander Gietelink Oldenziel, Jesse Hoogland, and others.
Overview
The seminar consists of two parts. You can find a tentative schedule here.
Week 1: "The Primer" (Virtual)
The first week will provide a comprehensive introduction to SLT and its relevance to AI alignment. The material is designed to be approachable if you have the equivalent of a technical undergraduate degree (e.g., in CS, math, or physics).
Participants will have the opportunity to learn from lectures covering topics such as thermodynamics, catastrophe theory, algebraic geometry, and SLT. There will also be sessions focused on experimental aspects of SLT and introductions to AI alignment and mechanistic interpretability.
Week 2: Advanced Topics and Collaboration (In Person)
The second week will delve deeper into the SLT and algebro-geometric foundations behind the toy models of superposition paper. This will serve as an application of the material covered in the first week, allowing participants to fully grasp the concepts and their relevance to AI alignment. The week will also feature presentations from researchers, open discussions, and opportunities for networking and collaboration.
Weekend: Hackathon
During the weekend, we will host a hackathon dedicated to developing novel SLT-based tools.
Registration
If you're interested in participating and want to receive updates please register by filling out this form. Further updates on event details will be provided to registered participants. We may no longer have spots available for in-person accommodation during the second week, but the remote option will be available to everyone.
We are excited to announce a two-week seminar on singular learning theory (SLT) and AI alignment, taking place
from June 19th to July 2nd in Berkeley. EDIT: The conference will have a two-part structure, June 19th-23rd virtual and June 24th-July 2nd in-person at Rose Garden Inn in Berkeley.SLT studies the relation between the geometry of the loss landscape and the computational properties of machines learning in that landscape. It builds on powerful theoretical and experimental machinery developed in (solid-state) physics, where it is the geometry of the energy landscape that determines the relevant properties of physical systems. SLT offers a path towards developing novel, scalable interpretability tools, in particular for studying and detecting phase transitions during training.
During this workshop, we'll bring together singular learning theorists and alignment researchers to connect and further the applications of singular learning theory to alignment. The workshop aims to familiarize alignment researchers with SLT, seed new research collaborations, and develop tools based on SLT ideas. There will be talks by Daniel Murfet, Susan Wei, Shaowei Lin, Alexander Gietelink Oldenziel, Jesse Hoogland, and others.
Overview
The seminar consists of two parts. You can find a tentative schedule here.
Week 1: "The Primer" (Virtual)
The first week will provide a comprehensive introduction to SLT and its relevance to AI alignment. The material is designed to be approachable if you have the equivalent of a technical undergraduate degree (e.g., in CS, math, or physics).
Participants will have the opportunity to learn from lectures covering topics such as thermodynamics, catastrophe theory, algebraic geometry, and SLT. There will also be sessions focused on experimental aspects of SLT and introductions to AI alignment and mechanistic interpretability.
Week 2: Advanced Topics and Collaboration (In Person)
The second week will delve deeper into the SLT and algebro-geometric foundations behind the toy models of superposition paper. This will serve as an application of the material covered in the first week, allowing participants to fully grasp the concepts and their relevance to AI alignment. The week will also feature presentations from researchers, open discussions, and opportunities for networking and collaboration.
Weekend: Hackathon
During the weekend, we will host a hackathon dedicated to developing novel SLT-based tools.
Registration
If you're interested in participating and want to receive updates please register by filling out this form. Further updates on event details will be provided to registered participants. We may no longer have spots available for in-person accommodation during the second week, but the remote option will be available to everyone.
Check out the website here.