|
Workshop
|
Sun 16:30
|
Token-token correlations predict the scaling of the test loss with the number of input tokens
Francesco Cagnetta · Matthieu Wyart
|
|
|
Workshop
|
|
Harnessing Loss Decomposition for Long-Horizon Wave Predictions via Deep Neural Networks
Indu Kant Deo · Rajeev Jaiman
|
|
|
Workshop
|
|
Loss-to-Loss Prediction: Language model scaling laws across datasets
David Brandfonbrener · Nikhil Anand · Nikhil Vyas · Eran Malach · Sham Kakade
|
|
|
Poster
|
Thu 16:30
|
Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
Qiang LI · Hoi-To Wai
|
|
|
Workshop
|
|
A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
Kairong Luo · Haodong Wen · Shengding Hu · Zhenbo Sun · Zhiyuan Liu · Maosong Sun · Kaifeng Lyu · Wenguang Chen
|
|
|
Workshop
|
|
Neural Operators as Fast Surrogate Models for the Transmission Loss of Parameterized Sonic Crystals
Jakob Wagner · Samuel Burbulla · Miguel de Benito Delgado · Johannes Schmid
|
|
|
Poster
|
Thu 16:30
|
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
Paul Krzakala · Junjie Yang · Rémi Flamary · Florence d'Alché-Buc · Charlotte Laclau · Matthieu Labeau
|
|
