Loading…
7-8 April, 2025
Paris, France
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for PyTorch Conference Europe 2026 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in CEST (UTC/GMT +2). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date."
Tuesday April 7, 2026 11:45 - 11:55 CEST


Jacobian descent (JD) is an extension of gradient descent supporting the optimization of vector-valued functions. This algorithm can be used to train neural networks with multiple loss functions (e.g. multi-task learning). JD iteratively updates the parameters of the model using the Jacobian matrix of the vector of losses (the matrix stacking each individual loss' gradient).

To support and extend our research, we have developed the TorchJD library. With it, it's easy and efficient to compute the Jacobians with respect to the model parameters, and to aggregate them into an update direction that is beneficial to every objective. In contrast, if we had averaged the losses and used gradient descent, the update would have been beneficial to the average loss, but may have actually increased one of the individual losses.

In this session, we will give a quick introduction to the theory behind Jacobian descent, and then show how to use TorchJD on a variety of use-cases, beyond multi-task learning.

Library: https://github.com/TorchJD/torchjd
Paper: https://arxiv.org/abs/2406.16232
Speakers
avatar for Pierre Quinton

Pierre Quinton

Teacher, EPFL
PhD in Information Theory and Master in Data Science, specializing in fundamental math and multi-objective optimization (MOO). I am the co-author of TorchJD, a PyTorch library for Jacobian Descent developed with Valerian, currently at ~300 GitHub stars. My work aims to translate complex... Read More →
avatar for Valérian Rey

Valérian Rey

Research Engineer, Simplex Lab
I graduated from EPFL with a MSc in Data Science in 2021. Since then, I worked as a Data Scientist as Withings, and I worked on Jacobian descent, initially as a side-project, but now as a full-time occupation. I now spend most of my time developing and maintaining TorchJD, and I love... Read More →
Tuesday April 7, 2026 11:45 - 11:55 CEST
Founders Cafe
  Training Systems

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Share Modal

Share this link via

Or copy link