9 papers with MLG authors to appear at ICLR 2024

10 papers with MLG authors will appear at ICLR 2024 in Vienna, Austria.

Stochastic Gradient Descent for Gaussian Processes Done Right Jihao Andreas Lin, Shreyas Padhy, Javier Antorán*, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz Friday, May 10, 09:45 – Poster Session 7

RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations Jiajun He, Gergely Flamich, Zongyu Guo, José Miguel Hernández-Lobato Friday, May 10, 09:45 – Poster Session 7

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks Samyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Edward Grefenstette, Tim Rocktäschel, David Scott Krueger Wednesday, May 8 16:30 – Poster Session 4

Reward Model Ensembles Help Mitigate Overoptimization Thomas Coste, Usman Anwar, Robert Kirk, David Krueger Tu, May 7, 10:45 – Poster Session 1

Repelling Random Walks  Isaac Reid, Eli Berger, Krzysztof Choromanski, Adrian Weller Tuesday, May 7, 16:30 – Poster Session 2

General Graph Random Features Isaac Reid, Krzysztof Choromanski, Eli Berger*, Adrian Weller Thursday, May 9, 10:45 – Poster Session 5

Transport meets Variational Inference: Controlled Monte Carlo Diffusions Francisco Vargas, Shreyas Padhy, Denis Blessing*, Nikolas Nüsken Tuesday May 9, 10:45 – Poster Session 1

Retro-fallback: retrosynthetic planning in an uncertain world Austin Tripp, Krzysztof Maziarz, Sarah Lewis, Marwin Segler, José Miguel Hernández-Lobato Wednesday, May 8, 16:30 – Poster Session 4

WORKSHOPS

Fast non-stationary geospatial modelling with multiresolution (wavelet) Gaussian processes Talay M Cheema, Carl Edward Rasmussen Tackling Climate Change with Machine Learning Workshop