If You Give a Mouse (two) Loss Functions : Multi Objective Optimization

Поделиться
HTML-код
  • Опубликовано: 17 ноя 2024

Комментарии • 63

  • @halibrahim
    @halibrahim Год назад +2

    Watching this video in the parking lot. Thank you and keep the good work. Short, precise, applied and to the point. This is how applied stat and econometrics should be taught.

  • @YouAreTheRaidBoss
    @YouAreTheRaidBoss 2 года назад +9

    You're a bloody legend Ritvik!
    I love learning from you but don't stress yourself.
    You're setting your own priorities and that's the way it should be!

    • @ritvikmath
      @ritvikmath  2 года назад +1

      Thank you for saying that :)

  • @galenseilis5971
    @galenseilis5971 2 года назад +3

    Somehow we got through the whole video without explicitly hearing about "Pareto efficiency" or "scalarization": well done.

  • @CodeEmporium
    @CodeEmporium 2 года назад +2

    Welcome back Ritvik :) Almost at 100K!! Super proud! Very well deserved!

  • @hengdashi
    @hengdashi 2 года назад +2

    glad to see you back man even tho it's a month late ❤

  • @maneeshajainz
    @maneeshajainz 5 месяцев назад

    You are absolutely amazing in explaining concepts!

  • @CptJoeCR
    @CptJoeCR 2 года назад +3

    The king returns!

  • @Mutual_Information
    @Mutual_Information 2 года назад +2

    Nice to see you back! Was wondering whether you had dropped RUclips. Glad to see you didn’t

  • @michaelrainer7487
    @michaelrainer7487 2 года назад +2

    Nobody I know can use a children's marker on paper or a white board with tons of stats on it but STILL make it so understandable and clear. A+ my friend.

  • @alexmash1353
    @alexmash1353 2 года назад +2

    Nice to see you back! Love your videos.

  • @randyng3336
    @randyng3336 2 года назад +1

    Welcome back Ritvit, you've been missed dearly!!

  • @bassoonatic777
    @bassoonatic777 2 года назад +1

    Welcome back! Missed your videos.

  • @GodsGrieff
    @GodsGrieff 2 года назад +3

    I love the background of your video.
    You should use it more...it's a lovely soothing place!

  • @rahulinvestdor6545
    @rahulinvestdor6545 2 года назад +3

    Keep going buddy, I love to learn from you.

  • @vidabk
    @vidabk 2 года назад +2

    great video . Please proceed ahead in this series and teach more about multi objective optimization.

  • @b0nce
    @b0nce 2 года назад +1

    Yeah, you're back :)
    Missed your videos

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w 2 года назад +1

    Great metaphor to start with.

  • @saisushanthdurvasulabitsian
    @saisushanthdurvasulabitsian 2 года назад +2

    Glad that you are back Ritvik 😊, isn’t this similar to lasso or ridge regression or in general regularised loss where the coefficient lambda determines the weight we give to regularisation vs minimising actual loss function and is dynamically tuned based on cv data

    • @ritvikmath
      @ritvikmath  2 года назад

      Great thought ! Lasso and Ridge can indeed be thought of as multi objective optimization problems too

    • @saisushanthdurvasulabitsian
      @saisushanthdurvasulabitsian 2 года назад

      @@ritvikmath thanks for the confirmation and reply

  • @golnoushghiasi7698
    @golnoushghiasi7698 2 года назад +1

    So happy you are back!

  • @conscious-atoms
    @conscious-atoms 2 года назад +1

    It feels so much easier to learn from you than from 500 pages books.
    I would also enjoy some more safety-oriented videos: adversarial robustness, interpretability, trojans, alignment, black swans...

    • @jasdeepsinghgrover2470
      @jasdeepsinghgrover2470 2 года назад

      You can follow works by NN Taleb on black swans and others. Especially the book Statistical Consequences of Fat Tails

    • @conscious-atoms
      @conscious-atoms 2 года назад

      @@jasdeepsinghgrover2470 These books look great, but it's a big time investment to read. I personally enjoyed the Center for AI safety's course, it's pretty thorough and includes exercises.

    • @jasdeepsinghgrover2470
      @jasdeepsinghgrover2470 2 года назад

      @@conscious-atoms Ohh... Would love to go through it

  • @rahulprasad2318
    @rahulprasad2318 2 года назад +3

    Based guruji returns 🎉🎉

  • @jasdeepsinghgrover2470
    @jasdeepsinghgrover2470 2 года назад

    Would love a more detailed video as well. Like on regularization as multi objective optimization

  • @rohitkhoiwal7803
    @rohitkhoiwal7803 2 года назад +6

    Can you share how you achieved this simulation? It will be really helpful for my assignment.

    • @washedtoohot
      @washedtoohot Год назад

      Would like to know this as well!

  • @manueltiburtini6528
    @manueltiburtini6528 2 года назад

    Thank you for your videos

  • @boukraailyesali9131
    @boukraailyesali9131 2 года назад +1

    Wich you talk about dynamic multi objective optimizations it is a fascinating domain(missils ...etc )

  • @ChocolateMilkCultLeader
    @ChocolateMilkCultLeader 2 года назад

    wlecome back to the GOAT

  • @jasdeepsinghgrover2470
    @jasdeepsinghgrover2470 2 года назад

    I think a linear combination of metrics is not that suitable even though it is very common. We should use the function of constraints that suits the kind of optimization. Like satisfier kind of constraints should have exponential costs if not satisfied and optimizer constraints should be linearly combined. Have seen this to work much better in papers for pose estimation where they need to get elbows and knees right

  • @Mars.2024
    @Mars.2024 6 месяцев назад

    great like always; Could you make more video about this concept and coding like running a real but simple project? 👩‍🏫

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w 2 года назад +2

    Can you show the math behind this in the future. Would be interesting.

  • @fhashim
    @fhashim Год назад

    Please do some tutorials of linear and non-linear optimisation

  • @michaelzumpano7318
    @michaelzumpano7318 2 года назад

    What, no math!!! I think you should do a follow up where you develop the equations. What is the relationship of dynamic multi-objective optimization to Lagrange multipliers or other convex optimization topics?

  • @m.taufiqaffandi
    @m.taufiqaffandi Год назад

    This is an amazing video! How to code the mouse-cat-cheese simulation btw?

  • @RaviShankar-de5kb
    @RaviShankar-de5kb 2 года назад +1

    woohooo!

  • @accountname1047
    @accountname1047 2 года назад +1

    Great video

  • @Septumsempra8818
    @Septumsempra8818 2 года назад

    How do we perform multi-variate sorts? Suppose you are trying to choose a portfolio of assets. I want to sort on return and risk. How do I get top 10 high return and low risk assets.
    P.S. I am an economist and know the theoretical way, but I can seem to easily apply it in this scenario.
    🇿🇼🇿🇦

  • @AbhayTiwari
    @AbhayTiwari 2 года назад +1

    Isn't it similar to three body problem in physics ?

    • @ritvikmath
      @ritvikmath  2 года назад

      I’ll need to look into it thanks !

  • @philipsalvo
    @philipsalvo 2 года назад

    do you have a notebook where this logic is exemplified?

  • @furqanhaider6839
    @furqanhaider6839 2 года назад

    Why is cat static and cheese mobile?

  • @imdkkashyap9115
    @imdkkashyap9115 2 года назад

    how to put fun target game number sir make video