|
Poster
|
Wed 9:00
|
Adversarial Reprogramming Revisited
Matthias Englert · Ranko Lazic
|
|
|
Poster
|
Thu 14:00
|
On Margin Maximization in Linear and ReLU Networks
Gal Vardi · Ohad Shamir · Nati Srebro
|
|
|
Poster
|
Wed 14:00
|
Vision Transformers provably learn spatial structure
Samy Jelassi · Michael Sander · Yuanzhi Li
|
|
|
Poster
|
Thu 14:00
|
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime
Benjamin Bowman · Guido Montufar
|
|
|
Workshop
|
|
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
Alex Damian · Eshaan Nichani · Jason Lee
|
|
|
Poster
|
Tue 14:00
|
Reconstructing Training Data From Trained Neural Networks
Niv Haim · Gal Vardi · Gilad Yehudai · Ohad Shamir · Michal Irani
|
|
|
Poster
|
Tue 9:00
|
Gradient Methods Provably Converge to Non-Robust Networks
Gal Vardi · Gilad Yehudai · Ohad Shamir
|
|
|
Poster
|
Wed 14:00
|
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
Zhiyuan Li · Tianhao Wang · Jason Lee · Sanjeev Arora
|
|
|
Workshop
|
Fri 8:00
|
Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples
Josue Ortega Caro
|
|
|
Poster
|
Thu 9:00
|
On the Frequency-bias of Coordinate-MLPs
Sameera Ramasinghe · Lachlan E. MacDonald · Simon Lucey
|
|
|
Poster
|
Tue 14:00
|
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias
Itay Safran · Gal Vardi · Jason Lee
|
|
|
Poster
|
Wed 9:00
|
Imbalance Trouble: Revisiting Neural-Collapse Geometry
Christos Thrampoulidis · Ganesh Ramachandra Kini · Vala Vakilian · Tina Behnia
|
|
