by Antonio Silveti-Falls Papers
2 papers found
Conference
Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness
Thomas Pethick, Wanyun Xie, Mete Erdogan et al.
NEURIPS 2025oralarXiv:2506.01913
7
citations
Training Deep Learning Models with Norm-Constrained LMOs
Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos et al.
ICML 2025spotlightarXiv:2502.07529
72
citations