HN

Comments (55)

• Menu

  armcat
  The real story here is this wonderful exposition in applying diffusion models to a time series data that is neither discrete nor continuous. It’s always fascinating to see diffusion models applied in different scenarios, same with diffusion language models.
• Menu

  stult
  There is no model of the market that can remain stably accurate because the market will inevitably incorporate the insights of any model that is accurate until those insights are no longer accurate
• arjie
  Remarkable internship. Fairly dense write-up too. Everything is informative.Amusing degree of detail, though it makes sense it’s targeted at future interns. Why would you expect order inter-arrival to be normal? Surely an order arriving sort of boosts the probability of others, Hawkes-like. A nice little trick to get students talking I suppose.Jane Street interns impressive as always.
• Menu

  alexpotato
  There is a great line in the Man Who Solved The Market [0] about RenTech:Paraphrasing:"They went out of their way to try and fill in gaps in the historical market data. Over time, they got so good at predicting prices movements that they built algorithms to fill in the gaps."Highly recommend the book if you are interested in the history of algorithmic trading.0 - https://amzn.to/4jNFpOS0 -
• efavdb
  For images, latent diffusion only works when using a special decoder that can produce realistic images given relevant samples from the latent space. This is trained like a GAN and doesn’t focus on pixel level error but higher level image features extracted via another network etc. expect that building a decoder like that for their problem may have solved their issues.
• dzink
  The market has modes and reverts behavior when it switches them. Thus happy bouncy becomes hammered stammered. The prediction models fall hook and sinker for that.
• Menu

  stratos123
  For more info on why flow-matching is more stable than DDIM, see Heitz 2023, which nicely explains how they're almost equivalent but DDIM corresponds to a differential equation with a 1/α term that diverges at the start of the denoising process, while flow-matching/IADB doesn't diverge: https://arxiv.org/abs/2305.03486
• Menu

  asanineassasin
  Can you deduce a companies plans from its actions (hiring, ordering,) long before it makes them public via AI?
• anon
  undefined
• torginus
  Not a money guy, but isn't measuring accuracy of a price model via least squares misguided?A model that predicts the market with 99% accuracy (1% LS error), but reacts to price changes in a delayed manner is not very valuable, while the same model that is early is basically a money printer.
• dintech
  This was really interesting and a lot to get done in a short internship, nevermind the public retrospective and hackernews appearance. Well done Kavish!
• Menu

  reedf1
  No
• Menu

  TheOtherHobbes
  "Past performance is not indicative of future results."
• ibraryunus
  [flagged]
• jnagaraj2109
  [flagged]
• anon
  undefined
• soltanov
  [flagged]
• anon
  undefined