In the second scale, we have 10 groups of 8 8 20 -dimensional variables.

Reconstruction results (best seen when zoomed in). Figure 1: (a) Input on the left and reconstructed image on the right for CelebA HQ 256. We would like to thank all the reviewers for positive and constructive feedback. Reconstruction: The reconstructed images in NV AE are indistinguishable from the training images (see Figure 1(a)). GANs are perhaps less prone to this, as they may drop modes without being penalized. Is the data conditioned on all zz z's: 's in their log space, and we limit Training curves: Figure 1 in the supplementary material demonstrates training stability with spectral regularization.

In the second scale, we have 10 groups of 8 8 20 -dimensional variables.

We propose Nouveau V AE (NV AE), a deep hierarchical V AE built for image generation using depth-wise separable convolutions and batch normalization.

Adversarial robustness of deep autoencoders (AEs) remains relatively unexplored, even though their non-invertible nature poses distinct challenges. Existing attack algorithms during the optimization of imperceptible, norm-bounded adversarial perturbations to maximize output damage in AEs, often stop at sub-optimal attacks. We observe that the adversarial loss gradient vanishes when backpropagated through ill-conditioned layers. This issue arises from near-zero singular values in the Jacobians of these layers, which weaken the gradient signal during optimization. We introduce GRILL, a technique that locally restores gradient signals in ill-conditioned layers, enabling more effective norm-bounded attacks. Through extensive experiments on different architectures of popular AEs, under both sample-specific and universal attack setups, and across standard and adaptive attack settings, we show that our method significantly increases the effectiveness of our adversarial attacks, enabling a more rigorous evaluation of AE robustness.