Jonathan Frankle: From Lottery Tickets to LLMs

Jonathan Frankle: From Lottery Tickets to LLMs

Author: Daniel Bashir October 26, 2023 Duration: 1:08:22
The Gradient: Perspectives on AI
TechnologyScience

In episode 96 of The Gradient Podcast, Daniel Bashir speaks to Jonathan Frankle.

Jonathan is the Chief Scientist at MosaicML and (as of release). Jonathan completed his PhD at MIT, where he investigated the properties of sparse neural networks that allow them to train effectively through his lottery ticket hypothesis. He also spends a portion of his time working on technology policy, and currently works with the OECD to implement the AI principles he helped develop in 2019.

Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pub

Subscribe to The Gradient Podcast:  Apple Podcasts  | Spotify | Pocket Casts | RSSFollow The Gradient on Twitter

Outline:

* (00:00) Intro

* (02:35) Jonathan’s background and work

* (04:25) Origins of the Lottery Ticket Hypothesis

* (06:00) Jonathan’s empiricism and approach to science

* (08:25) More Karl Popper discourse + hot takes

* (09:45) Walkthrough of the Lottery Ticket Hypothesis

* (12:00) Issues with the Lottery Ticket Hypothesis as a statement

* (12:30) Jonathan’s advice for PhD students, on asking good questions

* (15:55) Strengths and Promise of the Lottery Ticket Hypothesis

* (18:55) More Lottery Ticket Hypothesis Papers

* (19:10) Comparing Rewinding and Fine-tuning

* (23:00) Care in making experimental choices

* (25:05) Linear Mode Connectivity and the Lottery Ticket Hypothesis

* (27:50) On what is being measured and how

* (28:50) “The outcome of optimization is determined to a linearly connected region”

* (31:15) On good metrics

* (32:54) On the Predictability of Pruning Across Scales — scaling laws for pruning

* (34:40) The paper’s takeaway

* (38:45) Pruning Neural Networks at Initialization — on a scientific disagreement

* (45:00) On making takedown papers useful

* (46:15) On what can be known early in training

* (49:15) Jonathan’s perspective on important research questions today

* (54:40) MosaicML

* (55:19) How Mosaic got started

* (56:17) Mosaic highlights

* (57:33) Customer stories

* (1:00:30) Jonathan’s work and perspectives on AI policy

* (1:05:45) The key question: what we want

* (1:07:35) Outro

Links:

* Jonathan’s homepage and Twitter

* Papers

* The Lottery Ticket Hypothesis and follow-up work

* Comparing Rewinding and Fine-tuning in Neural Network Pruning

* Linear Mode Connectivity and the LTH

* On the Predictability of Pruning Across Scales

* Pruning Neural Networks at Initialization: Why Are We Missing The Mark?

* Desirable Inefficiency



Get full access to The Gradient at thegradientpub.substack.com/subscribe

Hosted by Daniel Bashir, The Gradient: Perspectives on AI moves beyond surface-level headlines to explore the intricate machinery and human ideas shaping artificial intelligence. Each episode is built on a foundation of deep research, leading to conversations that are both technically substantive and broadly accessible. You'll hear from researchers, engineers, and philosophers who are actively building and critiquing our technological future, discussing not just how AI systems work, but the larger implications of their integration into society. This isn't about speculative hype; it's a grounded examination of real progress, persistent challenges, and ethical considerations from those on the front lines. The discussions peel back layers on topics like model architecture, policy, and the fundamental science behind the algorithms becoming part of our daily lives. For anyone curious about the substance behind the buzz-whether you have a technical background or are simply keen to understand a defining technology of our age-this podcast offers a crucial and thoughtful resource. Tune in for a consistently detailed and nuanced take that treats artificial intelligence with the complexity it deserves.
Author: Language: English Episodes: 100

Official website RSS
spotify
The Gradient: Perspectives on AI
Podcast Episodes
Ted Gibson: The Structure and Purpose of Language [not-audio_url] [/not-audio_url]

Duration: 2:13:24
In episode 107 of The Gradient Podcast, Daniel Bashir speaks to Professor Ted Gibson.Ted is a Professor of Cognitive Science at MIT. He leads the TedLab, which investigates why languages look the way they do; the relatio…
Eric Jang: AI is Good For You [not-audio_url] [/not-audio_url]

Duration: 1:29:57
In episode 105 of The Gradient Podcast, Daniel Bashir speaks to Eric Jang.Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pubSubscribe to The Gradient Po…
2023 in AI, with Nathan Benaich [not-audio_url] [/not-audio_url]

Duration: 1:35:37
In episode 104 of The Gradient Podcast, Daniel Bashir speaks to Nathan Benaich.Nathan is Founder and General Partner at Air Street Capital, a VC firm focused on investing in AI-first technology and life sciences companie…
Kathleen Fisher: DARPA and AI for National Security [not-audio_url] [/not-audio_url]

Duration: 46:16
In episode 103 of The Gradient Podcast, Daniel Bashir speaks to Dr. Kathleen Fisher.As the director of DARPA’s Information Innovation Office (I2O), Dr. Kathleen Fisher oversees a portfolio that includes most of the agenc…
Peter Tse: The Neuroscience of Consciousness and Free Will [not-audio_url] [/not-audio_url]

Duration: 2:24:04
In episode 102 of The Gradient Podcast, Daniel Bashir speaks to Peter Tse.Professor Tse is a Professor of Cognitive Neuroscience and chair of the department of Psychological and Brain Sciences at Dartmouth College. His r…
Vera Liao: AI Explainability and Transparency [not-audio_url] [/not-audio_url]

Duration: 1:37:03
In episode 101 of The Gradient Podcast, Daniel Bashir speaks to Vera Liao.Vera is a Principal Researcher at Microsoft Research (MSR) Montréal where she is part of the FATE (Fairness, Accountability, Transparency, and Eth…
Thomas Dietterich: From the Foundations [not-audio_url] [/not-audio_url]

Duration: 2:01:57
In episode 100 of The Gradient Podcast, Daniel Bashir speaks to Professor Thomas Dietterich.Professor Dietterich is Distinguished Professor Emeritus in the School of Electrical Engineering and Computer Science at Oregon…
Martin Wattenberg: ML Visualization and Interpretability [not-audio_url] [/not-audio_url]

Duration: 1:42:05
In episode 99 of The Gradient Podcast, Daniel Bashir speaks to Professor Martin Wattenberg.Professor Wattenberg is a professor at Harvard and part-time member of Google Research’s People + AI Research (PAIR) initiative,…

«12345678910»