Sanath Kumar Krishnamurthy

Research Scientist at Meta. Before that I was a PhD Student at Stanford.

[Aishwarya Mandyam @Aishwarya_R_M]

✨Excited to announce our new paper on adaptive interventions for behavioral health change 🏃‍♂️, to appear at CHIL 2024 🏙️, now available on arxiv! https://t.co/HETbWUem2h

[Vasilis Syrgkanis @syrgkanis]

Excited to share our new applied causal machine learning book https://t.co/fmT2byqlWk is available online. Any feedback/corrections greatly appreciated!

[Ben Recht @beenwrekt]

Since we just wrapped up an AI megaconference, it felt like a good day to plead for fewer papers. https://t.co/ha6tkSKxhB

[Golub Capital Social Impact Lab @GSBsiLab]

Personalized policies are valuable but learning them requires data

Compared to RCTs, adaptive experiments for non-personalized policy learning improve in-experiment outcomes and the value of policy learned at the end

Can they reliably serve personalized policy learning? 🧵

[Emma Brunskill @EmmaBrunskill]

Curious about contextual bandits with theoretical bounds that balance cumulative regret and simple regret? Come check out Sanath’s poster :
Wed 10:45 am - Great Hall and Hall B1+B2 (level 1) #1914. Jt w @Susan_Athey and Ruohan Zhan https://t.co/fP8ttSReqE #NeurIPS2023

[Golub Capital Social Impact Lab @GSBsiLab]

Which charity is your perfect match?

Our 6-question quiz is here to guide you to a highly-rated charity that satisfies both your heart and mind. It’s time to meet your charity soulmate!

Click here https://t.co/Q4vtYvno6V #CharitySoulmate #GivingTuesday

[Demis Hassabis @demishassabis]

Researchers from @googledeepmind and @googleAI have published CoDoC, which explores how we could harness human-AI collaboration in hypothetical medical settings to deliver the best results https://t.co/NZd7zTqkJM

[Golub Capital Social Impact Lab @GSBsiLab]

Contextual bandits adaptively learn a treatment assignment policy that maps individual characteristics into assigned actions, balancing exploration/exploitation tradeoffs. This forthcoming #AIStats2023 paper adapts ML/CI insights to this problem 1/6

https://t.co/7twv4HctiI