# jemdoc: menu{MENU}{talks.html}, showsource = Nadav Cohen --- Blog Posts [http://www.offconvex.org/2022/01/06/gf-gd/ *Does gradient flow over neural networks really represent gradient descent?*] \n [http://www.offconvex.org/ Off the Convex Path], Jan'22. [http://www.offconvex.org/2021/07/08/imp-reg-tf/ *Implicit regularization in tensor factorization: can tensor rank shed light on generalization in deep learning?*] \n [http://www.offconvex.org/ Off the Convex Path], Jul'21. [http://www.offconvex.org/2020/11/27/reg_dl_not_norm/ *Can implicit regularization in deep learning be explained by norms?*] \n [http://www.offconvex.org/ Off the Convex Path], Nov'20. [http://www.offconvex.org/2019/07/10/trajectories-linear-nets/ *Understanding implicit regularization in deep learning by analyzing trajectories of gradient descent*] \n [http://www.offconvex.org/ Off the Convex Path], Jul'19. [http://www.offconvex.org/2018/11/07/optimization-beyond-landscape/ *Understanding optimization in deep learning by analyzing trajectories of gradient descent*] \n [http://www.offconvex.org/ Off the Convex Path], Nov'18. [http://www.offconvex.org/2018/03/02/acceleration-overparameterization/ *Can increasing depth serve to accelerate optimization?*] \n [http://www.offconvex.org/ Off the Convex Path], Mar'18.