Do the main claims made in the abstract and introduction accurately reflect the paper's Did you discuss any potential negative societal impacts of your work? Did you state the full set of assumptions of all theoretical results? If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [No] The code will Did you specify all the training details (e.g., data splits, hyperparameters, how they Did you report error bars (e.g., with respect to the random seed after running experiments multiple times)? Did you include the total amount of compute and the type of resources used (e.g., type Did you include any new assets either in the supplemental material or as a URL? [N/A] Did you discuss whether and how consent was obtained from people whose data you're If you used crowdsourcing or conducted research with human subjects... (a) We trained backdoored model for 100 epochs using Stochastic Gradient Descent (SGD) with an initial learning rate of 0.1 on CIFAR-10 and the ImageNet subset (0.01 on GTSRB), a weight decay of The learning rate was divided by 10 at the 20th and the 70th epochs. The details of backdoor triggers are summarized in Table 5. ASR: attack success rate; CA: clean accuracy.

This paper studies a long-standing problem of learning the representations of a whole graph without human supervision.

In many learning problems, the domain scientist is often interested in discovering thegroups offeatures that areredundant and areimportant forclassification.

This statement is not a guarantee of global optimum for LHS (i.e,I(ˆX;X)), but rather a justifica-30 tion of why maximizing LHS can lead to desirable redundancies in RHS (i.e.I(X;X|Z) = 0). By using neural31 network, we have experimentally shown (for genetic and MNIST) that it is sufficiently flexible to achieve highly32 accurate results.

All simulations were based on pytorch [5]. For the nonlinear neuroscience tasks, we applied the gradient descent method "Adam" [4] to the recurrent weights W as well as to the input and output vectors mi, wi. We checked that our results did not depend qualitatively on the choice of the "Adam" algorithm over plain gradient descent; however, training converged more easily for this choice of algorithm. We also checked that restricting training to W only (as for the simple model) did not alter our results qualitatively (although, with this restriction, training on the Romo task for small values of g did not converge). Code for reproducing our results can be found on https://github.com/frschu/neurips_