Sliding down the stairs: how correlated latent variables accelerate learning with neural networksby Lorenzo Bardone,…
Towards Learning Stochastic Population Models by Gradient Descentby Justin N. Kreikemeyer, Philipp Andelfinger, Adelinde M.…
Variational Stochastic Gradient Descent for Deep Neural Networksby Haotian Chen, Anna Kuzina, Babak Esmaeili, Jakub…
On the Convergence of Continual Learning with Adaptive Methodsby Seungyub Han, Yeongmo Kim, Taehyun Cho,…
New logarithmic step size for stochastic gradient descentby M. Soheil Shamaee, S. Fathi Hafshejani, Z.…
How Private are DP-SGD Implementations?by Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi,…
Certified Machine Unlearning via Noisy Stochastic Gradient Descentby Eli Chien, Haoyu Wang, Ziang Chen, Pan…
Convergence of a model-free entropy-regularized inverse reinforcement learning algorithmby Titouan Renard, Andreas Schlaginhaufen, Tingting Ni,…
On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyondby Bohan Wang,…
Cyclical Log Annealing as a Learning Rate Schedulerby Philip NaveenFirst submitted to arxiv on: 13…