Nick Korbit

Hi, I'm Nick! I am a PhD student at IMT Lucca in the DYSCO lab, supervised by Mario Zanon and Alberto Bemporad. I work on practical second-order methods for large-scale machine learning, with an emphasis on Gauss-Newton approximation, matrix-free solvers, and JAX-native training systems.

Prior to starting my PhD, I worked on autonomous delivery robots at Starship Technologies and risk modeling at CompatibL.

Google Scholar  /  GitHub  /  LinkedIn

I work on making second-order optimization practical for large-scale machine learning. My research develops structured Gauss-Newton approximations, matrix-free solvers, and JAX-native training methods that reduce the compute and memory costs of curvature-aware optimization while preserving useful second-order information.

We introduce Somax, a systems framework for curvature-aware training that treats a second-order update as a planned JIT-compiled step. It exposes curvature operators, solvers, preconditioners, damping policies, and telemetry as composable modules, and shows that planning and module choices materially affect overhead and time-to-accuracy.

We present EGN, a stochastic second-order optimizer that computes the Gauss-Newton direction by solving an exact low-rank system in mini-batch space, making second-order updates practical when the parameter dimension is much larger than the batch size.

We propose IGND, a scale-invariant, easy-to-tune, fast-converging stochastic optimization algorithm based on approximate second-order information with nearly the same per-iteration complexity as Stochastic Gradient Descent.

I develop and maintain Somax, an open-source JAX library for curvature-aware training. It provides a composable framework for implementing, studying, and benchmarking a wide range of second-order methods.

Somax is an Optax-native JAX library for building and running curvature-aware optimizers. It provides modular curvature operators, estimators, solvers, preconditioners, and damping policies behind a common step interface, making second-order methods easier to compose, benchmark, and extend.

Machine Learning Experiments for Researchers (Winter 2026)
IMT School for Advanced Studies Lucca
Course Co-creator and Instructor
Practical companion to the Machine Learning course by Prof. Alberto Bemporad

Machine Learning Experiments for Researchers (Winter 2025)
IMT School for Advanced Studies Lucca
Course Co-creator and Instructor
Practical companion to the Machine Learning course by Prof. Alberto Bemporad

Kudos to Jon Barron for this template!