[HN Gopher] The difficulty of computing stable and accurate neur...
       ___________________________________________________________________
        
       The difficulty of computing stable and accurate neural networks
        
       Author : programd
       Score  : 46 points
       Date   : 2022-03-19 16:41 UTC (2 days ago)
        
 (HTM) web link (www.pnas.org)
 (TXT) w3m dump (www.pnas.org)
        
       | cs702 wrote:
       | Huh. I can read and understand the abstract and the introduction,
       | but I can't judge the work after a first pass. This is the kind
       | of paper that _cannot_ be easily skimmed, because it consists
       | almost entirely of densely packed pages chock-full of highly
       | abstract mathematical reasoning.
       | 
       | Not surprisingly, the authors are mathematicians. They claim to
       | _prove_ that
       | 
       | * there are well-conditioned problems for which suitable DNNs
       | exist, but no training algorithm can find arbitrarily good
       | approximations of those suitable DNNs;
       | 
       | * it's possible to find approximations of those suitable DNNs
       | only if we sacrifice digits of accuracy -- i.e., the
       | approximations cannot be arbitrarily good; and
       | 
       | * there is a class of DNNs they propose, which they call "fast
       | iterative restated networks" or FIRENETs, that solve undetermined
       | systems of linear equations over the complex numbers, with a good
       | blend of stability (robustness to adversarial samples) and
       | accuracy (within the claimed theoretical limits).
       | 
       | Finally, the authors provide open-source code (A+ for doing that,
       | but... Matlab!!??): https://www.github.com/Comp-Foundations-and-
       | Barriers-of-AI/f...
       | 
       | Does anyone else here understand the work better than me? I would
       | love an informal explanation that appeals to intuition.
        
         | lp251 wrote:
         | This is a follow-up to an earlier paper on instabilities in NN-
         | based solutions to inverse problems:
         | https://www.pnas.org/doi/10.1073/pnas.1907377117
         | 
         | Your statements appear to be a good summary of the paper.
        
           | cs702 wrote:
           | > Your statements appear to be a good summary of the paper.
           | 
           | Thanks. I found the authors' claims relatively easy to grok.
           | What I'd like to understand, intuitively, is how they got
           | there!
        
             | lp251 wrote:
             | Ah, sorry, I can't help too much there.
             | 
             | I skimmed through the proofs in the SI. Many of the tools
             | they use are taken from the compressed sensing literature
             | (robust null space property, sqrt LASSO paths, sample
             | complexity for CS-MRI style problems...).
             | 
             | I can point you to additional reading, if you'd like.
        
         | glitchc wrote:
         | What's wrong with Matlab? It works very well for this, as it's
         | very stable for numerical modeling work.
        
           | cs702 wrote:
           | It's closed-source; it lacks the kind of
           | tooling/infrastructure you need for working with larger,
           | state-of-the-art DNNs; and very little AI research is done
           | with it, limiting the audience that can can use the code.
           | Python -- or even Julia -- would have been a better choice.
        
             | lp251 wrote:
             | The story has changed somewhat recently, but up until ~2020
             | most ML for Inverse Problems research was done in Matlab,
             | especially for MRI and CT reconstruction. Thinking of
             | FBPNet and ADMM-Net.
        
       | sjg007 wrote:
       | Interesting work. A DNN is after all something that compresses
       | the input data and hopefully generalizes well over the domain.
       | This 'machine' itself will adhere to principles of Kolmogorov
       | complexity etc..
       | 
       | Traditionally, empirical solutions in the NN literature to
       | address instability are regularization and dropout.
       | 
       | Also, adding layers seems to improve things. The famous example
       | is XOR which cannot be trained by a single layer NN.
       | 
       | How do the theoretical limitations in the paper relate to these?
       | if at all...
        
       | kettleballroll wrote:
       | PNAS is not exactly the venue of first choice for publishing AI
       | research, so heuristically speaking, this article is likely not
       | worth the reading time. Furthermore neither the abstract nor the
       | first few words of the introduction give me any reason to read
       | on. I'm going to assume this is irrelevant, until someone here
       | can convince me it's not.
        
         | karpierz wrote:
         | They're showing that there are classes of problems that neural
         | networks cannot be trained to consistently approximate,
         | regardless of the amount of data provided. It sounds like
         | you're not interested in the limitations of neural networks, so
         | this paper isn't really relevant to you.
        
         | pizza wrote:
         | You would take the opinion of a random stranger on HN over the
         | article getting past peer reviewed and published in PNAS.. Why
         | that heuristic?
        
           | exdsq wrote:
           | OP greatly overestimates the knowledge of the average HN
           | user!
        
           | kettleballroll wrote:
           | I'm a researcher in the field, and the amount of new research
           | coming out each day is just way too big to handle. Which
           | means I have to rely on heuristics like this to judge what is
           | worth my time. Otherwise I'd be spending 25 hours/day reading
           | papers, and waste brain capacity digesting worthless
           | findings. Not everything that passes peer review is read-
           | worthy, far from it. It just means there aren't any gaping
           | holes in it. Don't get me wrong, the heuristic is far from
           | perfect. But a random paper on HN (which is not known for its
           | abundance of researchers) that was posted without any context
           | explaining why I should care is not a good signal.
        
             | exdsq wrote:
             | If you're a researcher in the field is it not a fundamental
             | skill to be able to make these judgement calls yourself?
             | And if wasted time is a concern to you, what makes you
             | think others would be willing to put in the time to try and
             | convince a random academic that they should or shouldn't
             | read a paper where they've not even specified _what_ they
             | 'd want to get out of it?
        
             | sjg007 wrote:
             | I am a researcher in this field and PNAS is fine medium to
             | communicate. This paper actually first appeared in arxiv
             | which is where everything seems to go first. Having it go
             | from arvix to PNAS is a good indicator that it is a good
             | paper, and it is! It would be a shame to dismiss it.
             | 
             | Hinton's paper in 2006 on reducing dimensionality with NNs
             | appeared in Science and nobody paid attention to that
             | either at the time.
        
         | rmellow wrote:
         | You might as well say it's not worth interviewing anyone who
         | didn't graduate from an Ivy League school, "heuristically
         | speaking".
         | 
         | Innovation can come from anywhere. Either we can take time to
         | evaluate something on its merits (if you have the competency
         | and resources), or leave it be (if you don't), or we accept to
         | be told what is true by institutions with their own interests,
         | who will use their position to further leverage them. And in
         | this path, knowledge is no longer free.
         | 
         | I will read further, but this paper is attacking a real issue
         | with neural nets.
        
           | RicoElectrico wrote:
           | Still, the choice of journal is pretty weird. Occam's razor:
           | If you have any results that feel significant and not just to
           | bump your publication count (the title would imply former)
           | you'd run with it to present on NIPS, ICLR, ICML or submit to
           | JMLR.
        
             | dchftcs wrote:
             | It's fair point that it's hard to spend time on something
             | if it doesn't carry enough promise. I've seen enough
             | crackpots from good universities that don't get called out
             | enough. They still exist on the likes of NeurIPS/ICML
             | though.
             | 
             | However, to me this appears to be serious work (whether or
             | not it's remarkable). Crackpots often obscure their
             | message, but here they state their premise quite clearly,
             | and skimming through the arguments they seem sane and
             | approachable.
        
           | hhmc wrote:
           | > You might as well say it's not worth interviewing anyone
           | who didn't graduate from an Ivy League school, "heuristically
           | speaking".
           | 
           | I know this isn't the point you were going for, but this _is_
           | a heuristic that is deployed in some companies/institutions
           | (at least the UK variant certainly is).
        
             | exdsq wrote:
             | > I know this isn't the point you were going for, but this
             | _is_ a heuristic that is deployed in some
             | companies/institutions (at least the UK variant certainly
             | is).
             | 
             | Which companies/institutions are you thinking of?
        
           | kettleballroll wrote:
           | Innovation can come from anywhere, but the authors of this
           | paper chose to submit to a venue that is outside the focus of
           | ML research. From what I understand, this paper would've been
           | a great fit for COLT (or even a general/broad ML conference
           | like ICML) and since it wasn't submitted (or wasn't
           | accepted), i think it makes sense to assume that it was
           | written by authors who either chose to circumvent the
           | community, or were rejected by it. I don't find your
           | comparison to ivy league fitting, because while there are
           | still a significant number of great candidates from non ivy
           | leagues, the number of great ML papers that have not been
           | published at top tier ML venues is in the single digits --
           | most researchers I know would rather just upload their paper
           | to arxiv and move on, rather than publishing in 2nd tier
           | venues. Which should tell you how much of a bad signal the
           | wrong venue can be in ML research.
           | 
           | Granted, it could also be that this was authored by people
           | outside of the field who.sont know the rules, but given how
           | much research gets published each day, it's impossible not to
           | rely on heuristics, especially since this paper was.posted
           | without context.
        
         | exdsq wrote:
         | If signaling is what gets you off, it might help that the
         | authors are based at Cambridge
        
       ___________________________________________________________________
       (page generated 2022-03-21 23:02 UTC)