iiinova — where your digital self keeps evolving

Nicholas Lourie

@nicholaslourie.bsky.social

Better empirical methods for deep learning & NLP. PhD at NYU. Advised by He He and @kyunghyuncho.bsky.social. Prev: @ai2.bsky.social. I build things. 🤖

Posts Replies Media

Reposted by Nicholas Lourie

NYU Center for Data Science @nyudatascience.bsky.social · 23/01/2026

Tuning AI models no longer needs to rely on expensive guesswork. Courant PhD student Nick Lourie, CDS Professor @kyunghyuncho.bsky.social, and CDS Assoc. Prof. He He reveal an important new statistical tool to estimate a model's best possible performance. nyudatascience.medium.com/taking-the-g...

nyudatascience.medium.com

Taking the Guesswork Out of AI Training: Hyperparameter Landscapes Are Simpler Than We Thought

Courant PhD student Nick Lourie shows a method that makes choosing hyperparameters more predictable and less reliant on trial and error.

011

Nicholas Lourie @nicholaslourie.bsky.social · 08/10/2025

📄🔈✨ Deep learning is an empirical science, but we rely on basic empirical methods. What might a better foundation—a simple theory—for empirical work look like? @kyunghyuncho.bsky.social, He He, and I move towards one in "Hyperparameter Loss Surfaces Are Simple Near their Optima" at #COLM2025! 🧵1/9

172

Reposted by Nicholas Lourie

Charlie Snell @seasnell.bsky.social · 26/11/2024

Can we predict emergent capabilities in GPT-N+1🌌 using only GPT-N model checkpoints, which have random performance on the task? We propose a method for doing exactly this in our paper “Predicting Emergent Capabilities by Finetuning”🧵

3456