Hattie Zhou: Lottery Tickets and Algorithmic Reasoning in LLMs

Hattie Zhou: Lottery Tickets and Algorithmic Reasoning in LLMs

Author: Daniel Bashir February 16, 2023 Duration: 1:42:59

In episode 60 of The Gradient Podcast, Daniel Bashir speaks to Hattie Zhou.

Hattie is a PhD student at the Université de Montréal and Mila. Her research focuses on understanding how and why neural networks work, based on the belief that the performance of modern neural networks exceeds our understanding and that building more capable and trustworthy models requires bridging this gap. Prior to Mila, she spent time as a data scientist at Uber and did research with Uber AI Labs.

Have suggestions for future podcast guests (or other feedback)? Let us know here!

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

Outline:

* (00:00) Intro

* (01:55) Hattie’s Origin Story, Uber AI Labs, empirical theory and other sorts of research

* (10:00) Intro to the Lottery Ticket Hypothesis & Deconstructing Lottery Tickets

* (14:30) Lottery tickets as lucky initialization

* (17:00) Types of masking and the “masking is training” claim

* (24:00) Type-0 masks and weight evolution over long training trajectories

* (27:00) Can you identify good masks or training trajectories a priori?

* (29:00) The role of signs in neural net initialization

* (35:27) The Supermask

* (41:00) Masks to probe pretrained models and model steerability

* (47:40) Fortuitous Forgetting in Connectionist Networks

* (54:00) Relationships to other work (double descent, grokking, etc.)

* (1:01:00) The iterative training process in fortuitous forgetting, scale and value of exploring alternatives

* (1:03:35) In-Context Learning and Teaching Algorithmic Reasoning

* (1:09:00) Learning + algorithmic reasoning, prompting strategy

* (1:13:50) What’s happening with in-context learning?

* (1:14:00) Induction heads

* (1:17:00) ICL and gradient descent

* (1:22:00) Algorithmic prompting vs discovery

* (1:24:45) Future directions for algorithmic prompting

* (1:26:30) Interesting work from NeurIPS 2022

* (1:28:20) Hattie’s perspective on scientific questions people pay attention to, underrated problems

* (1:34:30) Hattie’s perspective on ML publishing culture

* (1:42:12) Outro

Links:

* Hattie’s homepage and Twitter

* Papers

* Deconstructing Lottery Tickets: Zeros, signs, and the Supermask

* Fortuitous Forgetting in Connectionist Networks

* Teaching Algorithmic Reasoning via In-context Learning



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

The Gradient: Perspectives on AI
Podcast Episodes
Linus Lee: At the Boundary of Machine and Mind [not-audio_url] [/not-audio_url]

Duration: 2:28:46
In episode 56 of The Gradient Podcast, Daniel Bashir speaks to Linus Lee. Linus is an independent researcher interested in the future of knowledge representation and creative work aided by machine understanding of langua…
Suresh Venkatasubramanian: An AI Bill of Rights [not-audio_url] [/not-audio_url]

Duration: 1:40:58
In episode 55 of The Gradient Podcast, Daniel Bashir speaks to Professor Suresh Venkatasubramanian. Professor Venkatasubramanian is a Professor of Computer Science and Data Science at Brown University, where his research…
Melanie Mitchell: Abstraction and Analogy in AI [not-audio_url] [/not-audio_url]

Duration: 54:47
Have suggestions for future podcast guests (or other feedback)? Let us know here!In episode 53 of The Gradient Podcast, Daniel Bashir speaks to Professor Melanie Mitchell. Professor Mitchell is the Davis Professor at the…
Marc Bellemare: Distributional Reinforcement Learning [not-audio_url] [/not-audio_url]

Duration: 1:12:22
Have suggestions for future podcast guests (or other feedback)? Let us know here!In episode 52 of The Gradient Podcast, Daniel Bashir speaks to Professor Marc Bellemare. Professor Bellemare leads the reinforcement learni…
François Chollet: Keras and Measures of Intelligence [not-audio_url] [/not-audio_url]

Duration: 1:28:50
In episode 51 of The Gradient Podcast, Daniel Bashir speaks to François Chollet.François is a Senior Staff Software Engineer at Google and creator of the Keras deep learning library, which has enabled many people (includ…
Yoshua Bengio: The Past, Present, and Future of Deep Learning [not-audio_url] [/not-audio_url]

Duration: 1:14:09
Happy episode 50! This week’s episode is being released on Monday to avoid Thanksgiving. Have suggestions for future podcast guests (or other feedback)? Let us know here!In episode 50 of The Gradient Podcast, Daniel Bash…
Kanjun Qiu and Josh Albrecht: Generally Intelligent [not-audio_url] [/not-audio_url]

Duration: 47:21
In episode 49 of The Gradient Podcast, Daniel Bashir speaks to Kanjun Qiu and Josh Albrecht. Kanjun and Josh are CEO and CTO of Generally Intelligent, an AI startup aiming to develop general-purpose agents with human-lik…

«1...678910