Kimon Antonakopoulos

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness

Training Deep Learning Models with Norm-Constrained LMOs

Quantized Optimistic Dual Averaging with Adaptive Layer-wise Compression

Layer-wise Quantization for Quantized Optimistic Dual Averaging

Improving SAM Requires Rethinking its Optimization Formulation

Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness

Adaptive Bilevel Optimization