Common modifications include:(i)tuning attack parameters (e.g., number ofsteps),(ii)replacing network components to simplify the attack (e.g., removing randomization or non-differentiable components), and(iii) replacing the loss function optimized by the attack.

DNN pruning is an approach for deep model compression, which aimsateliminating someparameters withtolerable performance degradation.

While many techniques for detecting these attacks have been proposed, theyareeasily bypassed when theadversary hasfullknowledge of the detection mechanism and adapts the attack strategy accordingly. In this paper,we adopt anovel perspectiveand regard the omnipresence of adversarial perturbations asastrength rather thanaweakness.

Wedemonstrate that our visualization provides intuitive, detailed summaries of the learning dynamics beyond simple global measures (i.e., validation loss and accuracy), without the need to access validation data. Furthermore, M-PHATE better captures both the dynamics and community structure of the hidden units as compared to visualization based on standard dimensionality reduction methods (e.g., ISOMAP,t-SNE).

Actor-critic methods, a type of model-free Reinforcement Learning, have beensuccessfully applied to challenging tasks in continuous control, often achievingstate-of-the artperformance.

We present a novel framework for unsupervised object-centric 3D scene understanding that generalizes robustly to out-of-distribution images.

In this paper, we aim to eliminate the inductive bias imposed by the embedding space geometry.

Layer normalization (LayerNorm) is a technique to normalize the distributions of intermediate layers. It enables smoother gradients, faster training, and better generalizationaccuracy.

Motivatedbyrecent advances ingeometric representation learning, we propose a novel GNN architecture for learning representations on Riemannian manifolds with differentiable exponential and logarithmic maps.

Here, we integrate these two approaches by trading off utility, informativeness, and complexity in EC.