Africa
On the Limitations of Stochastic Pre-processing Defenses
Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such a defense is to apply a random transformation to inputs prior to feeding them to the model.
Position-based Scaled Gradient for Model Quantization and Pruning
We propose the position-based scaled gradient (PSG) that scales the gradient depending on the position of a weight vector to make it more compression-friendly.
Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization Ali Kavis
The selection of the step-size is of great importance in both the theoretical and practical performance of first-order methods, including the aforementioned VR methods.
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs.
Learning rule influences recurrent network representations but not attractor structure in decision-making tasks
RNN computation is valuable in two ways.
Noise Attention Learning: Enhancing Noise Robustness by Gradient Scaling
To handle this problem, a common idea is to force the model to fit only clean samples rather than mislabeled ones.