Summary of Effect Of Ambient-intrinsic Dimension Gap on Adversarial Vulnerability, by Rajdeep Haldar et al.
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerabilityby Rajdeep Haldar, Yue Xing, Qifan SongFirst submitted…
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerabilityby Rajdeep Haldar, Yue Xing, Qifan SongFirst submitted…
A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Networkby Ruichen Ma, Guanchao Qiao, Yian Liu, Liwei Meng,…
How Well Can Transformers Emulate In-context Newton’s Method?by Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris…
Stochastic gradient descent for streaming linear and rectified linear systems with adversarial corruptionsby Halyun Jeong,…
Parallel Algorithms for Exact Enumeration of Deep Neural Network Activation Regionsby Sabrina Drammis, Bowen Zheng,…
Deep Neural Network Initialization with Sparsity Inducing Activationsby Ilan Price, Nicholas Daultry Ball, Samuel C.H.…
On Minimal Depth in Neural Networksby Juan L. ValerdiFirst submitted to arxiv on: 23 Feb…
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Modelsby Chenyang Song, Xu Han,…
The effect of Leaky ReLUs on the training and generalization of overparameterized networksby Yinglong Guo,…
Generative Kaleidoscopic Networksby Harsh ShrivastavaFirst submitted to arxiv on: 19 Feb 2024CategoriesMain: Machine Learning (cs.LG)Secondary:…