[HN Gopher] How to solve computational science problems with AI:...
       ___________________________________________________________________
        
       How to solve computational science problems with AI: PINNs
        
       Author : mertkavi
       Score  : 32 points
       Date   : 2025-01-20 15:26 UTC (2 days ago)
        
 (HTM) web link (mertkavi.com)
 (TXT) w3m dump (mertkavi.com)
        
       | patrickkidger wrote:
       | FWIW - I used to do research in this area - PINNs are a terribly
       | overhyped idea.
       | 
       | See for example
       | https://www.nature.com/articles/s42256-024-00897-5
       | 
       | Classical solvers are very very good at solving PDEs. In contrast
       | PINNs solve PDEs by... training a neural network. Not once, that
       | can be used again later. But every single time you solve a new
       | PDE!
       | 
       | You can vary this idea to try to fix it, but it's still really
       | hard to make it better than any classical method.
       | 
       | As such the main use cases for PINNs -- they do have them! -- is
       | to solve awkward stuff like high-dimensional PDEs or nonlocal
       | operators or something. Here it's not that the PINNs got any
       | better, it's just that all the classical solvers fall off a
       | cliff.
       | 
       | ---
       | 
       | Importantly -- none of the above applies to stuff like neural
       | differential equations or neural closure models. These are
       | genuinely really cool and have wide-ranging applications.! The
       | difference is that PINNs are _numerical solvers_ , whilst
       | NDEs/NCMs are _techniques for modelling data_.
       | 
       | /rant ;)
        
         | __mmd wrote:
         | I believe a lot of this hype is purely attributable to
         | Karniadakis and how bad a lot of the methods in many areas of
         | engineering are. The methods coming out of CRUNCH (PINNs chief
         | among them) seem, if they are not just actually, more
         | intelligent in comparison, since engineers are happy to take a
         | solution to inverse or model selection problems by pure brute
         | force as "innovative" haha.
        
           | mnky9800n wrote:
           | I love karniadakis energy. I invited him to give a talk in my
           | research center ands his talk was fun and really targeted at
           | physicists who understand numerical computing. He gave a good
           | sell and was highly opinionated which was super welcomed. His
           | main argument was that these are just other ways to arrive
           | optimisation and they worked very quickly with only a bit of
           | data. I am sure he would correct me greatly at this point.
           | I'm not an expert on this topic but he knew the field very
           | well and talked at length about the differences between one
           | iterative method he developed and the method that Yao lai at
           | Stanford developed after I had her work on my mind because
           | she talked in an ai conference I organised in Oslo. I liked
           | that he seemed to be willing to disagree with people about
           | his own opinions because he simply believed he is correct.
           | 
           | Edit: this is the Yao lai paper I'm talking about:
           | 
           | https://www.sciencedirect.com/science/article/pii/S002199912.
           | ..
        
           | anon389r58r58 wrote:
           | The general rule of thumb to go by is that whatever
           | Karniadakis proposes, doesn't actually work outside of his
           | benchmarks. PINNs don't really work, and _his flavor_ of
           | neural operators also don't really work.
           | 
           | PINNs have serious problems with the way the "PDE-component"
           | of the loss function needs to be posed, and outside of
           | throwing tons of, often Chinese, PhD students, and postdocs
           | at it, they usually don't work for actual problems. Mostly
           | owed to the instabilities of higher order automatic
           | derivatives, at which point PINN-people begin to go through a
           | cascade of alternative approaches to obtain these higher-
           | order derivatives. But these are all just hacks.
        
         | mnky9800n wrote:
         | What do you do now?
        
       | Matthyze wrote:
       | Me and a friend were discussing PINNs, and he made an argument
       | against them: The Bitter Lesson. PINNs are a way of incorporating
       | domain knowledge into ML models. The Bitter Lesson, for those
       | unaware, is a famous essay by Rich Sutton that states that the
       | history of AI is full of attempts of methods guided by
       | domain/expert knowledge, but that ultimately, all such methods
       | were overtaken by methods that simply scaled data and/or
       | computation.
       | 
       | http://www.incompleteideas.net/IncIdeas/BitterLesson.html
       | 
       | I would love to hear HN's take on this argument.
        
         | add-sub-mul-div wrote:
         | Computer science is currently subservient to an economic
         | climate in which the only viable business is one that scales
         | revenue without scaling labor. That's the bitter lesson.
        
           | PaulHoule wrote:
           | But isn't that the story of technology and civilization?
           | Hunter-Gatherers produced no surplus and couldn't support a
           | complex and unequal society. Early agriculture could support
           | a pyramid, but not very high.
           | 
           | It used to be almost everyone worked in agriculture, now
           | about 1% does, so the others are free to _do something else_.
           | Prior to the microprocessor making a computer required manual
           | assembly of thousands of parts, early microprocessors
           | contained thousands of parts manufactured by a small number
           | of photographic and chemical steps, and the number of parts
           | has grown into the billions without the number of steps
           | expanding millions of times.
        
           | rangestransform wrote:
           | Improving labour productivity is good, actually
        
         | esafak wrote:
         | It works when data is cheap, and model size is not an issue.
        
         | nicoco wrote:
         | Scaling data is not always possible. It's really hard to get
         | your hands on good labelled medical imaging data, for instance.
         | Maybe it makes sense to try to incorporate insights from
         | biology and physiological instead of hoping that the neural net
         | will "get it" from seeing enough data.
        
       | roger_ wrote:
       | This articles seems like it was at least partially written by AI.
       | Lots of fluff and no clear explanation of what PINNs are and how
       | they work (other than the code).
        
         | getnormality wrote:
         | Agreed. Stylistic hints include the heavy use of bulleted lists
         | with bold headings, and the general lack of concern with
         | justifying any vaguely plausible-sounding assertion ("The PINN
         | approach ensures physical consistency, efficient computation,
         | and accurate generalization from limited data.")
         | 
         | I think someone who cared about the specific content would at
         | least note that linear PDEs like the heat equation often have
         | closed-form solutions and/or efficient algorithms for solving
         | any particular problem, so aren't likely to be usefully solved
         | with PINNs.
        
       ___________________________________________________________________
       (page generated 2025-01-22 23:00 UTC)