[HN Gopher] Generalized Orders of Magnitude
       ___________________________________________________________________
        
       Generalized Orders of Magnitude
        
       https://github.com/glassroom/generalized_orders_of_magnitude
        
       Author : leokoz8
       Score  : 24 points
       Date   : 2025-10-09 13:08 UTC (7 days ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | fheinsen wrote:
       | repo:
       | 
       | https://github.com/glassroom/generalized_orders_of_magnitude
        
         | dang wrote:
         | We'll add that link to the toptext as well. Thanks!
        
           | Alive-in-2025 wrote:
           | Thank you for things like this, it significantly enhances
           | news.yc to make these kinds of tweaks and choices.
        
       | cs702 wrote:
       | This is basically a Pytorch library for executing computations
       | over dynamic ranges that exceed Float64's limits, including on
       | GPUs.
       | 
       | I can see how it could be useful when you really need it. Thank
       | you for sharing it on HN.
       | 
       | I tried the sample code for estimating Lyapunov exponents in
       | parallel. It worked on the first try, and it was much faster than
       | existing methods, as advertised. It's _nice_ to come across
       | something that works as advertised on the first try!
       | 
       | The high-dynamic-range RNN stuff may be interesting to others,
       | but it's not for me. In my book, Transformers have won. Nowadays
       | it's so easy to whip-up a small Transformer with a few lines of
       | Python, and it will work well on anything you throw at it.
        
       | LolWolf wrote:
       | Hmm, how does this compare to things like
       | 
       | https://github.com/cjdoris/LogarithmicNumbers.jl
       | 
       | or
       | 
       | https://github.com/cjdoris/HugeNumbers.jl
       | 
       | (Apart from the PyTorch impl)
       | 
       | In particular, it feels like storing the complete complex number
       | is a bit silly since we know, a priori, that the number
       | exponentiates to +-1, so, wouldn't this mean that we have wasted
       | 31 bits? (=32-1 since only one bit is needed for the sign.)
       | 
       | That being said, this representation is very useful for certain
       | scenarios, of course, when you know that the dynamic range of
       | your number is very large, but, as far as I can tell, it's not
       | exactly super novel, unless I'm missing something!
        
       ___________________________________________________________________
       (page generated 2025-10-16 23:00 UTC)