|
Poster
|
Tue 9:00
|
Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization
Yuri Kinoshita · Taiji Suzuki
|
|
|
Poster
|
|
Generalization Bounds for Gradient Methods via Discrete and Continuous Prior
Xuanyuan Luo · Bei Luo · Jian Li
|
|
|
Poster
|
Tue 9:00
|
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
Jason Altschuler · Kunal Talwar
|
|
|
Poster
|
Tue 9:00
|
Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
Antonio Orvieto · Simon Lacoste-Julien · Nicolas Loizou
|
|
|
Workshop
|
|
Gradient dynamics of single-neuron autoencoders on orthogonal data
Nikhil Ghosh · Spencer Frei · Wooseok Ha · Bin Yu
|
|
|
Poster
|
Thu 14:00
|
On the difficulty of learning chaotic dynamics with RNNs
Jonas Mikhaeil · Zahra Monfared · Daniel Durstewitz
|
|
|
Poster
|
Thu 9:00
|
Langevin Autoencoders for Learning Deep Latent Variable Models
Shohei Taniguchi · Yusuke Iwasawa · Wataru Kumagai · Yutaka Matsuo
|
|
|
Workshop
|
|
Dynamic Efficient Adversarial Training Guided by Gradient Magnitude
Fu Wang · Yanghao Zhang · Wenjie Ruan · Yanbin Zheng
|
|
|
Workshop
|
Fri 12:35
|
Dynamic Efficient Adversarial Training Guided by Gradient Magnitude
Fu Wang · Yanghao Zhang · Wenjie Ruan · Yanbin Zheng
|
|
|
Poster
|
|
High-dimensional limit theorems for SGD: Effective dynamics and critical scaling
Gerard Ben Arous · Reza Gheissari · Aukosh Jagannath
|
|
|
Workshop
|
|
On Equivalences between Weight and Function-Space Langevin Dynamics
Ziyu Wang · Yuhao Zhou · Ruqi Zhang · Jun Zhu
|
|
|
Poster
|
Wed 9:00
|
Constrained Langevin Algorithms with L-mixing External Random Variables
Yuping Zheng · Andrew Lamperski
|
|
