home.social

#sparsity — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #sparsity, aggregated by home.social.

  1. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models The key idea The key idea Offloading local dependencies between tokens with lookups to a massive embedding t...

    #memory #sparsity #LLM

    Origin | Interest | Match
  2. 'A minimax optimal approach to high-dimensional double sparse linear regression', by Yanhang Zhang, Zhifan Li, Shixiang Liu, Jianxin Yin.

    jmlr.org/papers/v25/23-0653.ht

    #sparse #thresholding #sparsity

  3. 'skscope: Fast Sparsity-Constrained Optimization in Python', by Zezhi Wang, Junxian Zhu, Xueqin Wang, Jin Zhu, Huiyang Pen, Peng Chen, Anran Wang, Xiaoke Zhang.

    jmlr.org/papers/v25/23-1574.ht

    #sparse #optimization #sparsity

  4. #mistral's 8x22B is ~260GB

    the trend is to get models smaller, not bigger

    #pruning, #sparsity, #quantization, #distillation

    so why such a huge model?

    does mistral have no other models?

  5. The last talk of the second day of #DIPOpt, by Remi Grinonval, “Rapture of the deep: highs and lows of sparsity in a world of depths”.
    #Sparsity #inverseproblems

  6. Yasuhisa Kuroda released a spectral data processing program for chemical analysis called SPANA eonet.ne.jp/~spana-lsq/index-e. He has been kind enough to incorporate our BEADS algorithm (baseline estimation & denoising w/ #sparsity) to separate peaks, baseline and noise using sparsity priors! doi.org/10.1016/j.chemolab.201 #analyticalchemistry

  7. 'Fundamental limits and algorithms for sparse linear regression with sublinear sparsity', by Lan V. Truong.

    jmlr.org/papers/v24/21-0543.ht

    #sparse #sparsity #interpolation

  8. New podcast from @thegradient with Hattie Zhou (twitter: twitter.com/oh_that_hat):

    `Lottery Tickets and Algorithmic Reasoning in LLMs`

    thegradientpub.substack.com/p/

    The first half is focused on the lottery ticket hypothesis, which is a favorite topic of mine.

    #ML #sparsity #LLMs