ICML Poster "activation functions" Papers
6 papers found
A sampling theory perspective on activations for implicit neural representations
Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko et al.
ICML 2024posterarXiv:2402.05427
Initial Guessing Bias: How Untrained Networks Favor Some Classes
Emanuele Francazi, Aurelien Lucchi, Marco Baity-Jesi
ICML 2024posterarXiv:2306.00809
Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?
Huy Nguyen, Pedram Akbarian, Nhat Ho
ICML 2024posterarXiv:2401.13875
On dimensionality of feature vectors in MPNNs
César Bravo, Alexander Kozachinskiy, Cristobal Rojas
ICML 2024posterarXiv:2402.03966
ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate
Chenghao Liu, Minghua Chen
ICML 2024poster
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
Xiang Cheng, Yuxin Chen, Suvrit Sra
ICML 2024posterarXiv:2312.06528