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
Antoine Blondeau: Alpha Intelligence Capital and Investing in AI [not-audio_url] [/not-audio_url]

Duration: 59:34
In episode 78 of The Gradient Podcast, Daniel Bashir speaks to Antoine Blondeau.Antoine is a serial AI entrepreneur and Co-Founder and Managing Partner of Alpha Intelligence Capital. He was chief executive at Dejima when…
Joon Park: Generative Agents and Human-Computer Interaction [not-audio_url] [/not-audio_url]

Duration: 2:21:25
In episode 77 of The Gradient Podcast, Daniel Bashir speaks to Joon Park.Joon is a third-year PhD student at Stanford, advised by Professors Michael Bernstein and Percy Liang. He designs, builds, and evaluates interactiv…
Christoffer Holmgård: AI for Video Games [not-audio_url] [/not-audio_url]

Duration: 1:09:06
In episode 76 of The Gradient Podcast, Andrey Kurenkov speaks to Dr Christoffer HolmgårdDr. Holmgård is a co-founder and the CEO of Modl.ai, which is building AI Engine for game development. Before starting the company,…
Riley Goodside: The Art and Craft of Prompt Engineering [not-audio_url] [/not-audio_url]

Duration: 59:42
In episode 75 of The Gradient Podcast, Daniel Bashir speaks to Riley Goodside. Riley is a Staff Prompt Engineer at Scale AI. Riley began posting GPT-3 prompt examples and screenshot demonstrations in 2022. He previously…
Talia Ringer: Formal Verification and Deep Learning [not-audio_url] [/not-audio_url]

Duration: 1:45:35
In episode 74 of The Gradient Podcast, Daniel Bashir speaks to Professor Talia Ringer.Professor Ringer is an Assistant Professor with the Programming Languages, Formal Methods, and Software Engineering group at the Unive…
Brigham Hyde: AI for Clinical Decision-Making [not-audio_url] [/not-audio_url]

Duration: 41:43
In episode 72 of The Gradient Podcast, Daniel Bashir speaks to Brigham Hyde.Brigham is Co-Founder and CEO of Atropos Health. Prior to Atropos, he served as President of Data and Analytics at Eversana, a life sciences com…
Scott Aaronson: Against AI Doomerism [not-audio_url] [/not-audio_url]

Duration: 1:09:32
In episode 72 of The Gradient Podcast, Daniel Bashir speaks to Professor Scott Aaronson. Scott is the Schlumberger Centennial Chair of Computer Science at the University of Texas at Austin and director of its Quantum Inf…
Ted Underwood: Machine Learning and the Literary Imagination [not-audio_url] [/not-audio_url]

Duration: 1:43:59
In episode 71 of The Gradient Podcast, Daniel Bashir speaks to Ted Underwood.Ted is a professor in the School of Information Sciences with an appointment in the Department of English at the University of Illinois at Urba…
Irene Solaiman: AI Policy and Social Impact [not-audio_url] [/not-audio_url]

Duration: 1:12:11
In episode 70 of The Gradient Podcast, Daniel Bashir speaks to Irene Solaiman.Irene is an expert in AI safety and policy and the Policy Director at HuggingFace, where she conducts social impact research and develops publ…
Drago Anguelov: Waymo and Autonomous Vehicles [not-audio_url] [/not-audio_url]

Duration: 1:05:23
In episode 69 of The Gradient Podcast, Daniel Bashir speaks to Drago Anguelov.Drago is currently a Distinguished Scientist and Head of Research at Waymo, where he joined in 2018. Earlier, he spent eight years at Google w…