Deep Learning
Learning with convolution and pooling operations in kernel methods
However, understanding the precise interplay between approximation and generalization in convolutional architectures remains a challenge.
SA Vi+ +: Towards End-to-End Object-Centric Learning from Real-World Videos
This compositional structure must be appreciated to predict future states of the world and to effect particular outcomes.
Multi-objective Deep Data Generation with Correlated Property Control
CorrV AE, that recovers semantics and the correlation of properties through disentangled latent vectors.
Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models
During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing operations. In this work, we present Spatially Sparse Inference (SSI), a general-purpose technique that selectively performs computation for edited regions and accelerates various generative models, including both conditional GANs and diffusion models.
Supplementary Material for " Deep Learning with Label Differential Privacy " A Missing Proofs A.1 Proof of Lemma 1 Proof of Lemma 1
RRTop-k is " -DP as desired. The training set contains 60,000 examples and the test set contains 10,000. On MNIST, Fashion MNIST, and KMNIST, we train the models with mini-batch SGD with batch size 265 and momentum 0.9. On CIFAR-10, we use batch size 512 and momentum 0.9, and train for 200 epochs. The learning rate is scheduled according to the widely used piecewise constant with linear rampup scheme.
