An in-person Cambridge-local meetup of the
Neural Information Processing Systems (NeurIPS) conference.
Neural Information Processing Systems (NeurIPS) conference.
The goal of this meetup is to bring students, researchers, and engineers from the greater Cambridge area (UK) together for an opportunity to meet and discuss machine learning research presented at NeurIPS. We also want to provide an opportunity for researchers to promote their work and meet people from their local community. The day will feature poster and panel sessions and in-person presentations.
Tentative Schedule
Friday, 8th of December, 2023
09:00
Welcome
11:00 - 12:30
Invited talks and spotlights
Emile Mathieu: Geometric Neural Diffusion Processes
Laurence Midgley: SE(3) Equivariant Augmented Coupling Flows
Isaac Reid: Quasi-Monte Carlo Graph Random Features
Tycho van der Ouderaa: Learning Layer-wise Equivariances Automatically using Gradients
Zak Shumaylov: The Curse of Recursion: Training on Generated Data Makes Models Forget
Lennie Wells: Deep CCA for Self-Supervised Learning
Fabian Falck: A Unified Framework for U-Net Design and Analysis
Francisco Vargas: Transport meets Variational Inference: Controlled Monte Carlo Diffusions
12:30 - 13:30
Lunch
13:30 - 14:00
Invited talks and spotlights
Mateo Espinosa Zarlenga: Learning to Receive Help: Intervention-Aware Concept Embedding Models
Bruno Mlodozeniec & Tor Fjelde: Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
Shreyas Padhy: Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
14:45 - 15:45
17:30 - 22:00
Networking event
with light snacks and drinks
The end
Organizers
Christian Cabrera-Jojoa
Vincent Dutordoir
Ieva Kazlauskaitė
Stratis Markou
Zak Shumaylov
Location
Address:
University's West Cambridge site
15 JJ Thomson Avenue
Cambridge CB3 0FD
Rooms:
Ground Floor - Lecture Theatre 1 and The Street
Any Questions? Email:
ik394 'at' cam.ac.uk
ik394 'at' cam.ac.uk
Sponsors
