Search Results for author:
Found 8 papers, 3 papers with code
Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript
Recent years have witnessed intensive research interests on training deep neural networks (DNNs) more efficiently by quantization-based compression methods, which facilitate DNNs training in two ways: (1) activations are quantized to shrink the memory consumption, and (2) gradients are quantized to decrease the communication cost.
HPL-ViT: A Unified Perception Framework for Heterogeneous Parallel LiDARs in V2V
It uses a graph-attention Transformer to extract domain-specific features for each agent, coupled with a cross-attention mechanism for the final fusion.
SoK: Privacy-Preserving Data Synthesis
As the prevalence of data analysis grows, safeguarding data privacy has become a paramount concern.
Understanding the Impact of Adversarial Robustness on Accuracy Disparity
More specifically, we demonstrate that while the constraint of adversarial robustness consistently degrades the standard accuracy in the balanced class setting, the class imbalance ratio plays a fundamentally different role in accuracy disparity compared to the Gaussian case, due to the heavy tail of the stable distribution.
Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond
We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks, where the protocols might differ between one another, yet a procedure of obtaining local gradients is implicitly shared.
Actor-critic is implicitly biased towards high entropy optimal policies
We show that the simplest actor-critic method -- a linear softmax policy updated with TD through interaction with a linear MDP, but featuring no explicit regularization or exploration -- does not merely find an optimal policy, but moreover prefers high entropy optimal policies.
Towards Understanding the Data Dependency of Mixup-style Training
Despite seeing very few true data points during training, models trained using Mixup seem to still minimize the original empirical risk and exhibit better generalization and robustness on various tasks when compared to standard training.
Second-order Information in First-order Optimization Methods
To the best of our knowledge, this is the first paper that seriously considers the necessity of square root among all adaptive methods.
