Hybrid Approach to Parallel Stochastic Gradient Descentby Aakash Sudhirbhai Vora, Dhrumil Chetankumar Joshi, Aksh Kantibhai…
Too Good to be True? Turn Any Model Differentially Private With DP-Weightsby David ZagardoFirst submitted…
Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysisby Hongkang Li, Meng Wang,…
Towards Efficient and Scalable Training of Differentially Private Deep Learningby Sebastian Rodriguez Beltran, Marlon Tobaben,…
Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary…
BrowNNe: Brownian Nonlocal Neurons & Activation Functionsby Sriram Nagaraj, Truman HickokFirst submitted to arxiv on:…
Bayes’ capacity as a measure for reconstruction attacks in federated learningby Sayan Biswas, Mark Dras,…
Towards Exact Gradient-based Training on Analog In-memory Computingby Zhaoxian Wu, Tayfun Gokmen, Malte J. Rasch,…
To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensionsby…
How Neural Networks Learn the Support is an Implicit Regularization Effect of SGDby Pierfrancesco Beneventano,…