“Twitter: https://twitter.com/jaschasd/status/1756930242965606582 ArXiv: https://arxiv.org/abs/2402.06184 Abstract: "Some fractals -- for instance those associated with the Mandelbrot and quadratic Julia sets -- are computed by iterating a function, and identifying the boundary between hyperparameters for which the resulting series diverges or remains bo…”
The boundary of neural network trainability is fractal
Some fractals -- for instance those associated with the Mandelbrot and quadratic Julia sets -- are computed by iterating a function, and identifying the boundary between hyperparameters for which the resulting series diverges or remains bounded. Neural network training similarly involves iterating an update function (e.g. repeated steps of gradient descent), can result in convergent or divergent behavior, and can be extremely sensitive to small changes in hyperparameters. Motivated by these similarities, we experimentally examine the boundary between neural network hyperparameters that lead to stable and divergent training. We find that this boundary is fractal over more than ten decades of scale in all tested configurations.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“The sister paper[1] contains the fractal dimensions of some of the images using a boxcount paper. [1]: https://arxiv.org/pdf/2402.06184.pdf”
“> Convolution Nice idea, but I'm also planning a book on advanced cuda programming, and I will cover convolutions there, I'll think if it is interesting to have some kind of cross chapter that is valid for both books. > Noises I cover those in normal mapping > anisotropy I have a full chapter on brdf that includes anysotropy for raster and raytracing, …”
- The boundary of neural network trainability is fractal ↗RafelMri · 2024-02-19 · 200 分