[HN Gopher] Guide to Machine Learning with Geometric, Topologica...
       ___________________________________________________________________
        
       Guide to Machine Learning with Geometric, Topological, and
       Algebraic Structures
        
       Author : johmathe
       Score  : 108 points
       Date   : 2024-07-15 16:19 UTC (6 hours ago)
        
 (HTM) web link (www.arxiv.org)
 (TXT) w3m dump (www.arxiv.org)
        
       | dpflan wrote:
       | The paper's references have some good ones for getting more
       | acquainted with these subjects; this one being a nice dense one
       | to start with:
       | 
       | - Geometric Deep Learning Grids, Groups, Graphs, Geodesics, and
       | Gauges: https://geometricdeeplearning.com/
        
       | funnygiraffe wrote:
       | Is geometric, topological, and algebraic ML/data analysis
       | actually used in the industry? It is certainly beautiful math.
       | However, during grad school I met a few pure math PhD students
       | who were saying that after finishing their PhD they will just go
       | into industry to do topological data analysis (this was about 10
       | years ago and ML wasn't yet as hyped up). However, I have never
       | heard of anybody actually having success on that plan.
        
         | dpflan wrote:
         | I believe a use-case(s) receiving attention is drug design,
         | protein design, chemical design, etc.
         | 
         | Here is a summer school by the London Geometry and Machine
         | Learning group where research topics are shared and discussed.
         | - https://www.logml.ai/
         | 
         | Here is another group, a weekly reading group on graphs and
         | geometry: https://portal.valencelabs.com/logg
        
           | funnygiraffe wrote:
           | Thanks. That's certainly very interesting. Albeit it seems to
           | me that the number of jobs doing geometric and topological
           | ML/AI work in the drug or protein design space would be quite
           | limited, because any discovery ultimately has to be validated
           | through a wet lab process (or perhaps phase 1-3 clinical
           | trials for drugs) which is expensive and time-consuming.
           | However, I'm very uninformed and perhaps there is indeed a
           | sizable job market here.
        
             | dpflan wrote:
             | I think the job market in general for this kind of stuff is
             | "small"; but you can find jobs. Look at Isomoprhic Labs for
             | example. There are new AI/ML companies that have emerged in
             | recent years, helped by success of things like AlphaFold. I
             | think your question is really: does this research actually
             | creates tangible results? If it did, it would be able to
             | create more jobs to support it by virtue of being
             | economically successfully and therefore growing?
        
           | heyitsguay wrote:
           | As someone who did an applied math PhD before drifting
           | towards ML, it's worth pointing out that these applied math
           | groups typically talk about applications, but the real
           | question is whether they are actually used for the stated
           | application in practice due to outperforming methods that use
           | less pretty math. Typically (in every case i have seen) the
           | answer is "no", and the mathematicians don't even really care
           | about solving the applied problems nor fully understand what
           | it would mean to do so. It's just a source of grant-
           | justifiable abstract problems.
           | 
           | I would love to be proven wrong though!
        
             | dpflan wrote:
             | Indeed, the ivory tower has nice chats and ideas and is a
             | cool place to hang out, but does application actually
             | occur.
        
         | llm_trw wrote:
         | I've had some success using hyperbolic embeddings for bert like
         | models.
         | 
         | It's not something that the companies I've worked for
         | advertised or wrote papers about.
        
           | jqgatsby wrote:
           | Hyperbolic embeddings have been an interest of mine ever
           | since the Max Nickel paper. Would love to connect directly to
           | discuss this topic if you're open. here's my email:
           | https://photos.app.goo.gl/1khCwXBsVBuEP6xF7
        
         | fjork wrote:
         | I don't think there's much use currently. But I kinda like the
         | direction of the paper anyway. Most mathematical objects in ML
         | have geometric or topological structure, implicitly defined. By
         | making that structure explicit, we at worst have a fresh new
         | perspective on some ML thing. Like how viewing the complex
         | numbers on a 2d cartesian plane often clicks more for students
         | compared to the dry algebraic perspective. So even in the worst
         | case I think there's some pedagogical clarity here.
        
       | itissid wrote:
       | One common theme I see in the paper(e.g. in protein folding) is:
       | 
       | "Identify what properties are important (geometry, algebra, topo)
       | and which one is an useful prior and then "use" the guide to
       | select an initial struct. This is probably harder than it
       | sounds(unlike bayesian priors which are more forgiving for one to
       | select, but quite like them in that they both require special
       | assumptions)."
       | 
       | I wonder: could one use it to bring together certain multimodal
       | data and a proposed network for a task? Like could one bring in
       | sensor, map topology, urban topology, pictures which have certain
       | properties and that help me use this guide to make a statement
       | like : "Street data could be embedded with Sensor data to do ABC
       | kind of inference using XYZ NNetwork structure because this paper
       | suggests that is a reasonable thing to do"?
        
         | uoaei wrote:
         | All machine learning is just embedding of various forms. If you
         | have a way to translate disparate types of data into a common
         | space, in ways that preserve inductive bias and information
         | content, you can then combine them for downstream tasks.
        
       | mjhay wrote:
       | I am 100% convinced that these kind of approaches will be what
       | delivers ML research from the current resource-hungry and
       | ungeneralizable status quo. Low-dimensional Euclidean geometry is
       | special. Higher-dimensional Euclidean spaces are less special.
       | Most real-life data is high-dimensional, not at all smooth, and
       | possessing a structure you cannot call Euclidean with a straight
       | face. Look at what works with tabular data (which is probably
       | most of what practitioners work with in the wild). It's gradient
       | boosted trees, not neural networks.
       | 
       | There is a fundamental mismatch between the data we usually work
       | with and the spaces we shove it into. Tools from algebraic
       | topology and geometry are old hat in physics. If anything, they
       | should be even more useful in ML.
        
         | Davidzheng wrote:
         | I heavily disagree with the statement "tools of algebraic
         | topology is old hat in physics"
        
           | BenoitP wrote:
           | Well, I consider Lorentz' work to be old hat. I can't find an
           | older example though.
           | 
           | https://en.m.wikipedia.org/wiki/Lorentz_group
        
         | OutOfHere wrote:
         | Comment is heavily exaggerated in every way.
        
       | mistrial9 wrote:
       | some people on this thread are asking about jobs. The bigger
       | picture here is that previously intractable problems are going to
       | be solved with a new combination of math, data and compute..
       | there are lots of commercial cases that will change dramatically.
       | How can individual people or small groups benefit from serious
       | problem solving, economically?
        
       | OutOfHere wrote:
       | Note that the GPU hardware is setup for Euclidean matrix
       | operations. Even if you had a deep structure learner, it won't
       | necessarily help you if you have to go back to emulating it on
       | Euclidean hardware.
        
       ___________________________________________________________________
       (page generated 2024-07-15 23:00 UTC)