|
Poster
|
Wed 15:00
|
Have it your way: Individualized Privacy Assignment for DP-SGD
Franziska Boenisch · Christopher Mühl · Adam Dziedzic · Roy Rinberg · Nicolas Papernot
|
|
|
Poster
|
Thu 8:45
|
A Unified Fast Gradient Clipping Framework for DP-SGD
Weiwei Kong · Andres Munoz Medina
|
|
|
Poster
|
Tue 15:15
|
Bounding training data reconstruction in DP-SGD
Jamie Hayes · Borja Balle · Saeed Mahloujifar
|
|
|
Workshop
|
|
SGD batch saturation for training wide neural networks
Chaoyue Liu · Dmitriy Drusvyatskiy · Misha Belkin · Damek Davis · Yian Ma
|
|
|
Workshop
|
|
High Probability Guarantees for Random Reshuffling
Hengxu Yu · Xiao Li
|
|
|
Workshop
|
|
Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
Xuheng Li · Yihe Deng · Jingfeng Wu · Dongruo Zhou · Quanquan Gu
|
|
|
Workshop
|
|
Neural network compression with heavy-tailed SGD
Yijun Wan · Abdellatif Zaidi · Umut Simsekli
|
|
|
Workshop
|
|
From Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGD
Benjamin, Bernard, Louis DUPUIS · Paul Viallard
|
|
|
Workshop
|
|
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
Ziqiao Wang · Yongyi Mao
|
|
|
Workshop
|
Fri 9:30
|
Aiming towards the minimizers: fast convergence of SGD for overparameterized problems, Dmitriy Drusvyatskiy
Dmitriy Drusvyatskiy
|
|
|
Workshop
|
Fri 7:00
|
DoG is SGD’s best friend: toward tuning-free stochastic optimization, Yair Carmon
Yair Carmon
|
|
|
Poster
|
Thu 8:45
|
Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
Junchi YANG · Xiang Li · Ilyas Fatkhullin · Niao He
|
|
