Appendix
–Neural Information Processing Systems
The appendix is organized as follows. In Appendix B we bound the Hessian of the network and introduce some technical lemmas. In Appendix D we put the aforementioned results together to prove Theorem 3.5. In Appendix E we explain the merit of Assumption 3.6. In Appendix F we describe the details of our experiments with a link to the relevant code. Our approach to generalization will be based on metric entropy (see, e.g., Wainwright, 2019), a We recall some basic definitions.
Neural Information Processing Systems
Aug-22-2025, 01:31:26 GMT